INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     velvet
    -0.07
     Bord
    -0.07
     basement
    -0.06
     десят
    -0.06
    Bars
    -0.06
    accountId
    -0.06
     resto
    -0.06
    atches
    -0.06
     Leg
    -0.06
     Verde
    -0.06
    POSITIVE LOGITS
     facilitates
    0.07
    -Key
    0.06
     AppConfig
    0.06
    šem
    0.06
    .s
    0.06
     án
    0.06
     للم
    0.06
    .people
    0.06
     Declaration
    0.06
    Không
    0.06
    Act Density 0.021%

    No Known Activations