diff --git a/logistic_regression.ipynb b/logistic_regression.ipynb
new file mode 100644
index 0000000..fc76088
--- /dev/null
+++ b/logistic_regression.ipynb
@@ -0,0 +1,142 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Logistic regression is a commonly used binary classification model, and it can be translated into o1js.\n",
+    "\n",
+    "Here's a step-by-step example of how to translate a scikit-learn logistic regression model to o1js:\n",
+    "\n",
+    "**Step 1: Export Model Parameters**\n",
+    "\n",
+    "In scikit-learn, a logistic regression model has two main parameters: the coefficients (`coef_`) and the intercept (`intercept_`). These parameters define the decision boundary of the model.\n",
+    "\n",
+    "Suppose we have the following scikit-learn model:\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.linear_model import LogisticRegression\n",
+    "import numpy as np\n",
+    "\n",
+    "# Sample data\n",
+    "X_train = np.array([[1.0, 2.0], [2.0, 3.0], [3.0, 4.0]])\n",
+    "y_train = np.array([0, 1, 0])\n",
+    "\n",
+    "# Create and fit a logistic regression model\n",
+    "clf = LogisticRegression()\n",
+    "clf.fit(X_train, y_train)\n",
+    "\n",
+    "# Export model parameters\n",
+    "coefficients = clf.coef_\n",
+    "intercept = clf.intercept_"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[[1.75964519e-06 2.03090830e-06]]\n",
+      "[-0.69312133]\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(coefficients)\n",
+    "print(intercept)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "\n",
+    "**Step 2: Map Features**\n",
+    "\n",
+    "Ensure you have a mapping between the feature names (if available) and their corresponding positions or indices in the input data. In this example, we have two features: Feature 0 and Feature 1.\n",
+    "\n",
+    "**Step 3: Initialize o1js Model**\n",
+    "\n",
+    "In o1js, we can represent a logistic regression model as follows:\n",
+    "\n",
+    "```javascript\n",
+    "class LogisticRegressionModel {\n",
+    "    constructor(coefficients, intercept) {\n",
+    "        this.coefficients = coefficients; // Coefficients array\n",
+    "        this.intercept = intercept; // Intercept value\n",
+    "    }\n",
+    "\n",
+    "    predict(input) {\n",
+    "        // Compute the dot product of coefficients and input, add the intercept, and apply sigmoid function\n",
+    "        const dotProduct = this.coefficients.reduce((sum, coeff, index) => {\n",
+    "            return sum + coeff * input[index];\n",
+    "        }, 0);\n",
+    "        const z = dotProduct + this.intercept;\n",
+    "        return sigmoid(z); // Apply sigmoid activation\n",
+    "    }\n",
+    "}\n",
+    "```\n",
+    "\n",
+    "**Step 4: Translate Activation Functions**\n",
+    "\n",
+    "Ensure you have an equivalent implementation of the sigmoid activation function in o1js. You can refer to previous responses for the implementation.\n",
+    "\n",
+    "**Step 5: Perform Predictions**\n",
+    "\n",
+    "Implement the prediction logic in o1js using the `predict` method of the `LogisticRegressionModel` class. The prediction involves computing the dot product of coefficients and input features, adding the intercept, and applying the sigmoid activation.\n",
+    "\n",
+    "**Step 6: Write Tests**\n",
+    "\n",
+    "Develop tests to verify that the translated o1js model produces the same or similar predictions as the scikit-learn model on a set of test data. This step is crucial to validate the accuracy of the translation.\n",
+    "\n",
+    "Here's a simple test case in o1js:\n",
+    "\n",
+    "```javascript\n",
+    "const model = new LogisticRegressionModel(coefficients, intercept);\n",
+    "const input = [2.5, 3.5]; // Test input features\n",
+    "\n",
+    "const prediction = model.predict(input);\n",
+    "\n",
+    "console.log(`Prediction: ${prediction}`);\n",
+    "```\n",
+    "\n",
+    "This code sets up the o1js logistic regression model and performs a prediction on a test input.\n",
+    "\n",
+    "**Step 7: Optimize and Validate**\n",
+    "\n",
+    "Optimize the o1js model for efficiency and validate its accuracy against the scikit-learn model on various datasets. Ensure that the translated model behaves consistently with the original scikit-learn model."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}