INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.98
     CreateTagHelper
    -0.97
    Personensuche
    -0.90
     Aram
    -0.86
    Tikang
    -0.83
    Viitteet
    -0.83
    makeConstraints
    -0.83
    Personendaten
    -0.82
    NameInMap
    -0.82
    IsContent
    -0.82
    POSITIVE LOGITS
     plugin
    2.88
    plugin
    2.86
     plugins
    2.71
     Plugin
    2.71
    plugins
    2.65
    Plugin
    2.64
     Plugins
    2.44
    Plugins
    2.32
     PLUG
    2.17
    lugin
    1.99
    Act Density 0.062%

    No Known Activations