INDEX
    Explanations

    HTML class attributes in the document

    New Auto-Interp
    Negative Logits
    Geplaatst
    -0.90
     referenties
    -0.84
    StructEnd
    -0.77
    تقاوى
    -0.76
     nakalista
    -0.75
    IVEREF
    -0.74
    setVerticalGroup
    -0.73
     <<<<<<<<<<<<<<
    -0.72
     estekak
    -0.72
    Hochspringen
    -0.71
    POSITIVE LOGITS
    KNOWN
    0.55
    ImageContext
    0.54
     div
    0.54
     G
    0.53
     ward
    0.52
    трим
    0.52
     old
    0.52
     led
    0.50
    Into
    0.49
    weile
    0.49
    Act Density 0.029%

    No Known Activations