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

    Neuronpedia

    INDEX
    Explanations

    ```

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     &'
    -0.08
    Driver
    -0.07
     Busty
    -0.07
     Кон
    -0.07
    TRAIN
    -0.07
     <%
    -0.07
    ters
    -0.07
     Also
    -0.06
    CW
    -0.06
     đu
    -0.06
    POSITIVE LOGITS
     uç
    0.07
    씬
    0.07
     distractions
    0.07
    (strict
    0.07
     הכולל
    0.07
     é
    0.07
    Więcej
    0.07
    债务
    0.07
     usually
    0.07
     papel
    0.07
    Act Density 0.029%

    No Known Activations