INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Ingles
    -0.65
     GoogleFonts
    -0.61
    ariato
    -0.60
     potato
    -0.53
    ANZE
    -0.53
     Ips
    -0.52
     Olig
    -0.52
     Slu
    -0.52
    anker
    -0.52
     spoiler
    -0.51
    POSITIVE LOGITS
    ViewFeatures
    0.83
    ########.
    0.78
    Personensuche
    0.69
    новниш
    0.60
    новништво
    0.54
    contentLoaded
    0.54
     gezet
    0.54
    ResumeLayout
    0.54
    ReusableCell
    0.50
    verwijspagina
    0.47
    Act Density 0.001%

    No Known Activations