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

    Neuronpedia

    INDEX
    Explanations

    quantities, measures, or complexity followed by "of"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    一般来说
    0.40
    Các
    0.39
     يوجد
    0.38
     இத
    0.38
    ようになりました
    0.37
    доне
    0.37
    Lav
    0.37
    ‌,
    0.36
    对于
    0.35
    rolog
    0.35
    POSITIVE LOGITS
     of
    0.99
     sebesar
    0.83
     của
    0.76
     של
    0.75
    of
    0.73
     của
    0.65
     totalling
    0.62
    ของ
    0.60
     totaling
    0.60
     amounting
    0.59
    Act Density 0.020%

    No Known Activations