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

    Neuronpedia

    INDEX
    Explanations

    different approaches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     on
    0.88
    telefono
    0.82
     are
    0.80
    tahun
    0.80
    tabla
    0.77
    0.73
    servicio
    0.72
    registro
    0.71
    tų
    0.70
     a
    0.69
    POSITIVE LOGITS
    ب
    1.08
    ,
    1.04
    is
    0.94
    ر
    0.94
    p
    0.86
    기
    0.86
    ing
    0.84
    к
    0.84
    ກ
    0.84
    ك
    0.82
    Act Density 0.072%

    No Known Activations