INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     stage
    -2.11
     Stage
    -1.25
     STAGE
    -1.23
    stage
    -1.20
    Stage
    -1.16
     screen
    -0.93
    STAGE
    -0.88
     escenario
    -0.81
     scène
    -0.75
    ステージ
    -0.74
    POSITIVE LOGITS
     فريبيس
    0.73
    StructEnd
    0.68
    省市镇
    0.68
    providedIn
    0.66
    Hentet
    0.65
    RectangleBorder
    0.63
     архивлан
    0.63
     onCancelled
    0.62
     CreateTagHelper
    0.59
    angliski
    0.58
    Act Density 0.216%

    No Known Activations