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

    Neuronpedia

    INDEX
    Explanations

    assert a function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    orderby
    1.62
    jaan
    1.61
    හ
    1.59
    isAdmin
    1.58
    Born
    1.56
    encodeWith
    1.55
     respectivas
    1.53
    chas
    1.50
     النساء
    1.50
     Süden
    1.49
    POSITIVE LOGITS
    ЕЛЬ
    1.96
    ాలు
    1.96
    Ро
    1.89
     mobs
    1.87
    Нет
    1.80
     avuto
    1.75
     immor
    1.74
     bezpeč
    1.70
    اب
    1.70
     vesicles
    1.68
    Act Density 0.009%

    No Known Activations