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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals, names, and organizational roles within discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    non-english or proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.45
     تضيفلها
    -0.44
    şiv
    -0.43
    ValueStyle
    -0.43
    لاعات
    -0.41
     GetEnumerator
    -0.41
    AndroidJUnit
    -0.40
    asticity
    -0.40
     defaultstate
    -0.40
    ⓧ
    -0.38
    POSITIVE LOGITS
    Lähteet
    0.47
     ویکی‌پدیا
    0.46
    🇶
    0.45
    findpost
    0.45
    KindOfClass
    0.44
    ource
    0.42
    țiunea
    0.41
    endpush
    0.41
     مرئيه
    0.41
    devamını
    0.40
    Act Density 0.096%

    No Known Activations