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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ل
    0.91
    รู้สึก
    0.82
    لین
    0.82
    是谁
    0.80
     médicament
    0.79
     bhikkhave
    0.77
    ્ષ
    0.77
    ذاء
    0.76
    ROIT
    0.75
    个月
    0.73
    POSITIVE LOGITS
    rom
    0.77
    ᅵ
    0.77
    improve
    0.75
     требует
    0.71
    ::
    0.71
    se
    0.71
     требуют
    0.69
     imply
    0.69
     применя
    0.69
     τη
    0.68
    Act Density 0.002%

    No Known Activations