INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     lòng
    -0.09
     throat
    -0.08
    _STATS
    -0.08
    _TIMER
    -0.07
    èce
    -0.07
    _INDEX
    -0.07
     Voting
    -0.07
     Bianca
    -0.07
    wür
    -0.07
    $/
    -0.07
    POSITIVE LOGITS
     коэффици
    0.08
     preceded
    0.08
     permitted
    0.08
     important
    0.08
     ±
    0.08
    0.08
    0.08
    قدر
    0.08
     kukho
    0.08
     gegeven
    0.07
    Act Density 0.031%

    No Known Activations