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

    Neuronpedia

    INDEX
    Explanations

    legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LOGIN
    -0.07
    _On
    -0.06
     هنگ
    -0.06
     majors
    -0.06
    irim
    -0.06
     worsh
    -0.06
    ang
    -0.06
     عصر
    -0.06
     judged
    -0.06
    ):(
    -0.06
    POSITIVE LOGITS
    بح
    0.07
    ваем
    0.07
     пласти
    0.06
    STATIC
    0.06
    érience
    0.06
    暗
    0.06
     fines
    0.06
    oui
    0.06
    fung
    0.06
    (features
    0.06
    Act Density 0.004%

    No Known Activations