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

    Neuronpedia

    INDEX
    Explanations

    Garment sizes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    课
    -0.07
    dirs
    -0.07
    _Msg
    -0.06
     příč
    -0.06
    \Helper
    -0.06
     Graz
    -0.06
    buch
    -0.06
     ци
    -0.06
     phim
    -0.06
    dbus
    -0.06
    POSITIVE LOGITS
     země
    0.06
    存档
    0.06
    ěl
    0.06
    的事情
    0.06
    AMPL
    0.06
    .pattern
    0.06
     instantiate
    0.06
    řez
    0.06
     країни
    0.06
    ToObject
    0.06
    Act Density 0.005%

    No Known Activations