INDEX
    Explanations

    structural elements and formatting in documents, such as punctuation and links

    New Auto-Interp
    Negative Logits
    UseVisualStyle
    -0.54
    tf
    -0.53
     smo
    -0.51
    mer
    -0.48
    AddTagHelper
    -0.48
     Charg
    -0.48
    Lever
    -0.48
     :
    
    -0.47
    FlatAppearance
    -0.47
     ez
    -0.46
    POSITIVE LOGITS
    Gemeinden
    0.68
    NameInMap
    0.67
    expandindo
    0.67
     Italijanski
    0.67
     réfrig
    0.67
    CloseOperation
    0.66
     nød
    0.64
    PreferredItem
    0.64
     setempat
    0.63
     pesada
    0.61
    Act Density 0.254%

    No Known Activations