INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     qualità
    0.74
    \
    0.73
    ле
    0.69
     piedi
    0.69
     njegova
    0.67
     yaz
    0.66
     može
    0.66
     probar
    0.66
    ită
    0.66
     température
    0.65
    POSITIVE LOGITS
    k
    1.00
    h
    0.87
    fashioned
    0.82
    history
    0.75
    z
    0.75
    kult
    0.75
    CK
    0.70
    funktion
    0.70
    timers
    0.68
    histor
    0.67
    Act Density 2.499%

    No Known Activations