Softmax Function Visualizer

Interactive visualization of the softmax activation function

About Softmax

The softmax function converts a vector of real numbers into a probability distribution. It's commonly used in machine learning for multi-class classification.

Formula: σ(z)_i = e^{z_i} / Σ_j e^{z_j}

Input Values

Input Values

Softmax Output

Key Insights

  • Softmax converts input values to probabilities that sum to 1
  • Higher input values get exponentially larger probabilities
  • The function is sensitive to differences between values
  • Adding a constant to all inputs doesn't change the output