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

    Neuronpedia

    INDEX
    Explanations

    safety and injury

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ج
    0.54
    지
    0.49
    タ
    0.48
    ط
    0.46
    ق
    0.45
    چ
    0.44
    נ
    0.43
    인
    0.42
    З
    0.42
    зить
    0.41
    POSITIVE LOGITS
     sóc
    0.50
    raining
    0.49
     ਸਿੰ
    0.47
     UIF
    0.47
     Config
    0.46
    ချုပ်
    0.45
     apron
    0.45
     reales
    0.45
     reals
    0.45
     aho
    0.45
    Act Density 0.008%

    No Known Activations