INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    _NAME
    -0.08
     name
    -0.07
    (image
    -0.07
     pedigree
    -0.07
    (target
    -0.07
    িম
    -0.07
    (transaction
    -0.07
    _MULT
    -0.07
     যত
    -0.07
    (name
    -0.07
    POSITIVE LOGITS
    0.09
     unhappy
    0.09
     गौर
    0.08
    ,美
    0.08
     beaut
    0.08
     dresser
    0.08
    строй
    0.08
     unfinished
    0.08
     woont
    0.08
    .Comp
    0.08
    Act Density 0.003%

    No Known Activations