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

    Neuronpedia

    INDEX
    Explanations

    data-driven decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.98
    া
    1.76
    y
    1.72
    ясь
    1.71
    ック
    1.65
    و
    1.64
    ्स
    1.63
    ла
    1.59
    ك
    1.55
    ch
    1.54
    POSITIVE LOGITS
    で
    1.64
    야
    1.63
     എന്നാൽ
    1.57
    ção
    1.46
    니다
    1.45
    可以说是
    1.45
    م
    1.43
    鸹
    1.41
     aastal
    1.37
    ('.')[
    1.36
    Act Density 0.009%

    No Known Activations