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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ذو
    -0.08
     Increases
    -0.08
     reserve
    -0.07
     yoga
    -0.07
    /operators
    -0.07
    URT
    -0.07
    bearer
    -0.07
    .Dataset
    -0.07
    _default
    -0.07
     Berg
    -0.07
    POSITIVE LOGITS
     with
    0.10
     the
    0.08
    0.08
    ów
    0.07
    ），
    0.07
    .getWriter
    0.07
    ,
    0.07
     QStringList
    0.07
    皙
    0.07
    匿
    0.06
    Act Density 0.083%

    No Known Activations