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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     a
    1.13
     I
    0.91
    AT
    0.74
    ﺭ
    0.72
    ﻮ
    0.68
    a
    0.65
     to
    0.63
    การ
    0.63
    AL
    0.63
     T
    0.61
    POSITIVE LOGITS
    ز
    1.02
    د
    1.02
    ка
    1.01
    و
    1.01
    ب
    1.01
    ला
    0.97
    ،
    0.95
    س
    0.94
    드
    0.93
    ك
    0.91
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.