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

    Neuronpedia

    INDEX
    Explanations

    provides support or enables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الذي
    0.49
     với
    0.48
     препаратов
    0.47
    诮
    0.47
     എടു
    0.46
    یک
    0.45
    హి
    0.45
     sépt
    0.45
    ڈ
    0.45
    وة
    0.45
    POSITIVE LOGITS
    itable
    0.49
    ancements
    0.46
     can
    0.41
    最初は
    0.41
     INTERNAL
    0.41
    ors
    0.40
    eslint
    0.40
     argc
    0.40
     일반적으로
    0.40
    crete
    0.40
    Act Density 0.012%

    No Known Activations