INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ImageType
    0.50
    ablanca
    0.45
     Ausnahme
    0.42
    izability
    0.42
    明る
    0.41
    amides
    0.40
    asshi
    0.40
    bohyd
    0.39
     ObjData
    0.39
    umberland
    0.39
    POSITIVE LOGITS
     Rainforest
    0.45
     Clarity
    0.44
     pulsing
    0.43
     Panorama
    0.43
     KFC
    0.42
     Pronto
    0.42
     QS
    0.42
     Puls
    0.42
     GS
    0.42
     LS
    0.41
    Act Density 0.001%

    No Known Activations