INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    enedor
    -0.07
     код
    -0.07
     explorer
    -0.06
     auditor
    -0.06
    cellent
    -0.06
     detay
    -0.06
     Coastal
    -0.06
    raya
    -0.06
    	M
    -0.06
    attended
    -0.06
    POSITIVE LOGITS
    %%%%%%%%
    0.07
     nag
    0.07
     К
    0.07
     paradigm
    0.06
    ilibrium
    0.06
     unveil
    0.06
    UAGE
    0.06
    QUEUE
    0.06
     eventName
    0.06
    _MIN
    0.06
    Act Density 0.129%

    No Known Activations