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

    Neuronpedia

    INDEX
    Explanations

    بحث عن

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cria
    2.05
     អ្នក
    1.94
     individuais
    1.91
     necessari
    1.86
     ಆದರೆ
    1.85
     fréquentes
    1.82
     ជា
    1.81
     ការ
    1.81
     យើង
    1.76
     lange
    1.76
    POSITIVE LOGITS
     من
    2.63
     ل
    2.60
     ف
    2.53
     لم
    2.49
     ت
    2.47
     ح
    2.46
     ب
    2.46
     ي
    2.45
     الت
    2.44
     وا
    2.44
    Act Density 0.017%

    No Known Activations