INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     ilişk
    0.43
     ફરિયા
    0.40
    തായ
    0.38
    ("~/
    0.37
    ählen
    0.37
     ofta
    0.36
    ٰی
    0.36
    lenia
    0.36
    0.36
    acuda
    0.35
    POSITIVE LOGITS
     hands
    1.41
    hands
    1.19
     handen
    1.15
     Hands
    1.13
    Hands
    1.11
     manos
    1.09
     mãos
    1.03
     हाथों
    1.00
     руках
    1.00
    手中
    0.97
    Act Density 0.008%

    No Known Activations