Implement the **softmax function**, a common output layer in deep learning that converts raw scores (logits) into a probability distribution. Softmax is defined as:
$$
\text{softmax}(z_i) = \frac{e^{z_i}}{\sum_{j=1}^{n} e^{z_j}}
$$

## Requirements

Implement the function
```python
import numpy as np

def softmax(logits):
    \"""
    Computes softmax probabilities from a list of logits.

    Args:
        logits (np.ndarray): Raw scores for each class.

    Returns:
        np.ndarray: Softmax probabilities (same length as logits), summing to 1.
    \"""
    # Your solution below
```

**Rules:**
- Ensure the input `logits` is a float array.
- Use a numerically stable approach by subtracting `max(logits)` before exponentiating.
- Return the result as a NumPy array.
- Do not use any prebuilt softmax utilities (e.g., `scipy.special.softmax`).
- Keep it as a single function with no helper classes.

## Example

```python
logits = [2.0, 1.0, 0.1]
softmax(logits)
```

Output:
```python
[0.6590, 0.2424, 0.0986]
```

Combination Sum III

Top #1 Songs Since 2005

Softmax

Solve this easy level ML coding question from General. The premier LeetCode for ML platform to master Python, SQL, and Machine Learning algorithms.

949. Softmax

Examples

Constraints

Similar Questions