INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    man
    -1.27
    MAN
    -1.14
     disambiguazione
    -1.10
    manship
    -0.90
    Personensuche
    -0.82
    MANS
    -0.82
    HostException
    -0.81
    Jeografia
    -0.80
     CreateTagHelper
    -0.77
    WriteBarrier
    -0.76
    POSITIVE LOGITS
    ly
    0.69
    eu
    0.60
    em
    0.59
    ed
    0.57
    ally
    0.57
    ek
    0.56
    lijke
    0.56
    ny
    0.54
    ages
    0.52
    ised
    0.51
    Act Density 0.016%

    No Known Activations