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

    Neuronpedia

    INDEX
    Explanations

    elaborate rituals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tır
    1.80
    ת
    1.70
     Clips
    1.48
    ü
    1.43
    ı
    1.39
    tol
    1.38
    tedir
    1.36
     Shifts
    1.35
    temperatur
    1.33
    ا
    1.31
    POSITIVE LOGITS
    f
    1.87
    z
    1.84
    c
    1.69
    ج
    1.63
     tainted
    1.57
    j
    1.48
    べき
    1.46
    ف
    1.44
     smack
    1.41
    ным
    1.38
    Act Density 0.516%

    No Known Activations