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

    Neuronpedia

    INDEX
    Explanations

    Reducing or minimizing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fatal
    -0.07
    .sf
    -0.07
    Heading
    -0.06
     protective
    -0.06
    vip
    -0.06
    منت
    -0.06
    ı
    -0.06
     kill
    -0.06
    attribute
    -0.06
     Lima
    -0.06
    POSITIVE LOGITS
    جن
    0.07
    -bind
    0.07
     Apost
    0.07
    [sizeof
    0.06
     appet
    0.06
    uestos
    0.06
    ーテ
    0.06
    _MOV
    0.06
    .getD
    0.06
     Anglic
    0.06
    Act Density 0.061%

    No Known Activations