INDEX
    Explanations

    Geometry variables

    New Auto-Interp
    Negative Logits
     "-"↵
    -0.08
    שא
    -0.08
    784
    -0.08
     настолько
    -0.07
     norwegian
    -0.07
    S
    -0.07
    对此
    -0.07
     rpm
    -0.07
     kms
    -0.07
     nec
    -0.07
    POSITIVE LOGITS
     facets
    0.08
    0.08
     Girls
    0.08
     pouss
    0.08
     ولك
    0.07
     conven
    0.07
     facet
    0.07
     Scholarship
    0.07
    ((*
    0.07
     claimed
    0.07
    Act Density 0.042%

    No Known Activations