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

    Neuronpedia

    INDEX
    Explanations

    coffee maker, table, mug

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ống
    0.89
    یتے
    0.87
     ایسا
    0.87
     kỹ
    0.86
    لع
    0.86
     учи
    0.85
     tecnica
    0.84
     پوچھ
    0.84
    ार्क
    0.83
     समय
    0.83
    POSITIVE LOGITS
    ة
    1.82
    ט
    1.41
    is
    1.34
     that
    1.28
    ing
    1.27
    ী
    1.26
    ות
    1.24
    ات
    1.23
     to
    1.18
    1.17
    Act Density 0.006%

    No Known Activations