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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    or
    0.96
    ai
    0.86
    at
    0.84
    on
    0.83
    as
    0.82
    rać
    0.80
    en
    0.80
    ent
    0.80
    2
    0.79
     a
    0.79
    POSITIVE LOGITS
    ﺱ
    0.87
    кновен
    0.85
     дру
    0.84
    હીં
    0.84
    ㄽ
    0.83
    இது
    0.82
    ভিয়েতনাম
    0.81
    ையு
    0.81
    гласно
    0.80
    நான்
    0.80
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.