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

    Neuronpedia

    INDEX
    Explanations

    specific professors, courses, research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    0.86
    or
    0.85
    as
    0.84
    ter
    0.80
    ah
    0.75
    an
    0.73
    ucapkan
    0.71
    ।
    0.69
    čí
    0.69
    on
    0.67
    POSITIVE LOGITS
    羰
    0.84
     produire
    0.83
    प्लीट
    0.82
     étendue
    0.82
    详
    0.77
     erythrocytes
    0.77
     degré
    0.76
     indépendant
    0.76
     inguinal
    0.76
     esboço
    0.76
    Act Density 0.002%

    No Known Activations