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

    Neuronpedia

    INDEX
    Explanations

    sorting lists of words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     doesn
    0.85
    不会
    0.79
     will
    0.77
     नहीं
    0.75
    也
    0.75
    你
    0.73
    ไม่
    0.72
     allows
    0.71
     don
    0.71
     ≠
    0.70
    POSITIVE LOGITS
     allerlei
    0.60
    ,_-
    0.58
     commande
    0.56
    აწილ
    0.56
     Radiat
    0.56
    yenne
    0.55
     Heterocycl
    0.55
    сійскай
    0.55
    ‌اند
    0.54
     massac
    0.54
    Act Density 2.092%

    No Known Activations