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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ders
    -0.07
    .position
    -0.07
     thems
    -0.06
    EndDate
    -0.06
    .getStatus
    -0.06
    -ext
    -0.06
     lever
    -0.06
     부탁
    -0.06
     мг
    -0.06
     KH
    -0.06
    POSITIVE LOGITS
    lášení
    0.07
     проход
    0.07
    .readline
    0.06
    ело
    0.06
    ераль
    0.06
     Cyril
    0.06
     ارزش
    0.06
    _sim
    0.06
    üğ
    0.06
    imming
    0.06
    Act Density 0.018%

    No Known Activations