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

    Neuronpedia

    INDEX
    Explanations

    concept of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    骚
    0.83
     вверх
    0.73
    FProperties
    0.73
    ടന
    0.73
    Основ
    0.73
    uitse
    0.72
     reasoning
    0.72
     للمع
    0.72
    keszt
    0.72
     Tutto
    0.71
    POSITIVE LOGITS
    of
    0.77
    Of
    0.72
    subcategory
    0.71
     of
    0.69
    category
    0.68
     फार
    0.67
    peripheral
    0.63
    consume
    0.63
    sub
    0.63
    că
    0.63
    Act Density 0.151%

    No Known Activations