INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     limit
    -0.10
     speeds
    -0.09
     speed
    -0.08
     Flutter
    -0.08
     permitted
    -0.08
    .limit
    -0.08
     mod
    -0.08
     pent
    -0.08
    лу
    -0.07
    (filter
    -0.07
    POSITIVE LOGITS
     καθ
    0.09
     osoba
    0.09
     лице
    0.09
    δες
    0.09
     лиц
    0.09
    akul
    0.08
    persona
    0.08
    consulta
    0.08
     Pessoa
    0.08
    ونات
    0.08
    Act Density 0.001%

    No Known Activations