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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     for
    0.66
     in
    0.57
    ك
    0.55
     as
    0.55
     продолжаем
    0.55
     steril
    0.54
    ت
    0.54
     حال
    0.52
    ing
    0.50
     l
    0.50
    POSITIVE LOGITS
    akkhan
    0.51
    apayati
    0.51
     Akash
    0.51
    텟
    0.51
    adocia
    0.48
    acuation
    0.47
     AppException
    0.47
     אטאטורק
    0.46
    షి
    0.46
    точ
    0.46
    Act Density 0.000%

    No Known Activations