INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     malware
    -0.07
    birthdate
    -0.06
     cry
    -0.06
    owe
    -0.06
    _version
    -0.06
     Cry
    -0.06
     Rentals
    -0.06
     gall
    -0.06
    .video
    -0.06
     semana
    -0.06
    POSITIVE LOGITS
     densely
    0.07
    کنان
    0.07
     wrongful
    0.07
     presenta
    0.07
    0.06
    	dfs
    0.06
    ieee
    0.06
    .oauth
    0.06
    ��
    0.06
     Buna
    0.06
    Act Density 0.117%

    No Known Activations