---
license: mit
tags:
- pytorch
- safetensors
- threshold-logic
- neuromorphic
---

# threshold-negator4bit

4-bit bitwise NOT (one's complement negation).

## Function

negator4bit(a3, a2, a1, a0) = [NOT(a3), NOT(a2), NOT(a1), NOT(a0)]

Inverts each bit independently.

## Truth Table (selected rows)

| Input | Output |
|-------|--------|
| 0000 | 1111 |
| 0001 | 1110 |
| 0101 | 1010 |
| 1111 | 0000 |

## Architecture

Single layer with 4 independent NOT neurons.

| Output | Weight on input | Bias |
|--------|-----------------|------|
| y3 | a3: -1 | 0 |
| y2 | a2: -1 | 0 |
| y1 | a1: -1 | 0 |
| y0 | a0: -1 | 0 |

Each neuron fires when its input is 0.

## Parameters

| | |
|---|---|
| Inputs | 4 |
| Outputs | 4 |
| Neurons | 4 |
| Layers | 1 |
| Parameters | 8 |
| Magnitude | 4 |

## Usage

```python
from safetensors.torch import load_file
import torch

w = load_file('model.safetensors')

def negator4(a3, a2, a1, a0):
    inp = torch.tensor([float(a3), float(a2), float(a1), float(a0)])
    return [int((inp * w[f'y{i}.weight']).sum() + w[f'y{i}.bias'] >= 0)
            for i in range(4)]

print(negator4(0, 1, 0, 1))  # [1, 0, 1, 0]
```

## License

MIT