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

    Neuronpedia

    INDEX
    Explanations

    therapy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _body
    -0.07
    Pets
    -0.06
     deterrent
    -0.06
     بدن
    -0.06
     面
    -0.06
    ande
    -0.06
    ñas
    -0.06
    endor
    -0.06
    ignment
    -0.06
     Womens
    -0.06
    POSITIVE LOGITS
    opc
    0.08
    -government
    0.07
    �
    0.06
    ์อ
    0.06
    973
    0.06
     таб
    0.06
     облад
    0.06
     sauce
    0.06
    -ip
    0.06
     overseeing
    0.06
    Act Density 0.004%

    No Known Activations