INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     ква
    0.52
    يه
    0.47
    ي
    0.43
    ين
    0.42
    يد
    0.42
     هاي
    0.42
     означа
    0.42
     Само
    0.41
    0.41
     вид
    0.41
    POSITIVE LOGITS
     analisi
    0.48
    0.47
     linguistics
    0.47
     radioactive
    0.47
     telah
    0.46
     vozila
    0.44
     artes
    0.43
     rumores
    0.43
     mayoral
    0.43
     crescita
    0.42
    Act Density 0.001%

    No Known Activations