INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     obyvatel
    -0.07
     floor
    -0.07
     голови
    -0.07
    思考
    -0.06
    .Summary
    -0.06
    ouflage
    -0.06
    _CONFIRM
    -0.06
     publik
    -0.06
     Audience
    -0.06
     synthes
    -0.06
    POSITIVE LOGITS
     EdgeInsets
    0.15
    Inset
    0.11
     inset
    0.08
     Insets
    0.08
     insets
    0.08
     UIEdgeInsets
    0.07
    Insets
    0.07
    EdgeInsets
    0.07
    	intent
    0.07
     wholes
    0.06
    Act Density 0.001%

    No Known Activations