INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    .Block
    -0.06
     Theme
    -0.06
     Led
    -0.06
    (holder
    -0.06
    urface
    -0.06
     QSize
    -0.06
     tehdy
    -0.06
     ranked
    -0.06
     Sigma
    -0.06
    bc
    -0.06
    POSITIVE LOGITS
    erialize
    0.07
    warm
    0.06
     پا
    0.06
    ascar
    0.06
     giy
    0.06
     :-
    0.06
    sil
    0.06
     possessions
    0.06
     RoundedRectangleBorder
    0.06
     hurl
    0.06
    Act Density 0.020%

    No Known Activations