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

    Neuronpedia

    INDEX
    Explanations

    variable assignments or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    你也
    0.48
     LPA
    0.48
     comprehensive
    0.47
     Pens
    0.46
     KL
    0.46
     prazo
    0.45
    リスト
    0.43
     CET
    0.43
     Пен
    0.43
    begin
    0.43
    POSITIVE LOGITS
    TimeSeries
    0.47
     paramagnetic
    0.45
     tumors
    0.45
    WaitingTime
    0.45
    cheduling
    0.43
    gäng
    0.43
    ching
    0.43
    zték
    0.43
    chester
    0.43
    HE
    0.42
    Act Density 0.001%

    No Known Activations