INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    OGND
    -0.57
     located
    -0.54
     springfox
    -0.46
    irvana
    -0.44
     AssemblyCulture
    -0.43
    Tembelea
    -0.43
    hyrchwyd
    -0.43
     negozio
    -0.43
     situés
    -0.42
     negozi
    -0.41
    POSITIVE LOGITS
    findpost
    0.71
    ArgsConstructor
    0.65
    ConstraintMaker
    0.62
    -------------</
    0.60
     thèse
    0.60
    athing
    0.60
     referrerpolicy
    0.58
    ItemLayout
    0.57
    denly
    0.55
    CastException
    0.55
    Act Density 0.546%

    No Known Activations