INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ##
    -0.09
    ###
    -0.08
     inf
    -0.07
     ##
    -0.07
     std
    -0.07
     backing
    -0.07
     Inf
    -0.07
     typeof
    -0.07
     incarnation
    -0.07
    .set
    -0.07
    POSITIVE LOGITS
    ед
    0.08
     Matters
    0.08
     aplicado
    0.08
     offent
    0.07
     дни
    0.07
    (Menu
    0.07
    _When
    0.07
    ënt
    0.07
    Menus
    0.07
    бран
    0.07
    Act Density 0.003%

    No Known Activations