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

    Neuronpedia

    INDEX
    Explanations

    variantes, leaks, enzima, anterior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ب
    2.31
    이지만
    1.80
     ardından
    1.75
    ти
    1.70
    니다
    1.70
    Ⴎ
    1.68
    та
    1.64
    有所
    1.64
    بك
    1.61
    ланды
    1.60
    POSITIVE LOGITS
    ра
    2.08
    ي
    1.54
    ib
    1.50
    fter
    1.49
    en
    1.48
    id
    1.48
     Enzyme
    1.44
    utilized
    1.43
    ד
    1.41
     antérieure
    1.40
    Act Density 0.000%

    No Known Activations