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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    é
    2.06
    도
    2.06
    你
    2.05
    늉
    2.02
     базе
    1.99
    有助于
    1.98
    ्स
    1.95
    에게
    1.86
    是我
    1.86
    राणिक
    1.83
    POSITIVE LOGITS
    ل
    2.52
    ка
    2.39
    у
    2.16
     rid
    2.09
     antérieure
    2.08
    ol
    2.03
    iatric
    1.99
    ร์
    1.98
    на
    1.95
    al
    1.93
    Act Density 0.291%

    No Known Activations