Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </em>
    1.28
    <strong>
    0.91
    ۀ
    0.87
    </strong>
    0.87
    <0xAF>
    0.85
    ۂ
    0.85
    --"
    0.83
     ✔
    0.83
    .'
    0.81
    Â
    0.80
    POSITIVE LOGITS
    ```
    4.11
     ```
    3.46
    $$
    2.81
    ｣
    2.70
    }$$
    2.64
    </th>
    2.52
    </h5>
    2.52
     $$
    2.43
    $$\
    2.43
    </h4>
    2.42
    Act Density 0.277%

    No Known Activations