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

    Neuronpedia

    INDEX
    Explanations

    cybersecurity authentication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يع
    1.10
    ني
    1.00
    ي
    0.96
    يز
    0.93
    في
    0.91
    يات
    0.90
     arouse
    0.89
    يلي
    0.89
    يلا
    0.87
    عي
    0.86
    POSITIVE LOGITS
     for
    0.89
    for
    0.89
    о
    0.84
    н
    0.83
    у
    0.81
     or
    0.80
     sekolah
    0.80
    and
    0.78
    il
    0.77
    ung
    0.75
    Act Density 0.006%

    No Known Activations