INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     isConnected
    -0.08
     earthquake
    -0.07
     bruises
    -0.07
    ewolf
    -0.07
     irresponsible
    -0.06
    .Bus
    -0.06
     Futures
    -0.06
    .GetKeyDown
    -0.06
    ifix
    -0.06
    Tpl
    -0.06
    POSITIVE LOGITS
     report
    0.07
     podem
    0.07
    هدف
    0.07
    👙
    0.07
    STA
    0.07
     contention
    0.06
     "[
    0.06
    .ny
    0.06
    :.
    0.06
    群众
    0.06
    Act Density 0.000%

    No Known Activations