INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    หัว
    -0.09
    צע
    -0.08
    -0.07
    кай
    -0.07
    .and
    -0.07
     herramientas
    -0.07
    ου
    -0.07
     préciser
    -0.07
    केत
    -0.07
    leri
    -0.07
    POSITIVE LOGITS
     equals
    0.09
     equality
    0.09
     между
    0.08
     совп
    0.08
     igualdad
    0.08
     eql
    0.08
     igualdade
    0.08
     FRANC
    0.08
     bridge
    0.08
     between
    0.08
    Act Density 0.059%

    No Known Activations