INDEX
Explanations
formatted output, likely from a table
New Auto-Interp
Negative Logits
متعلقه
-0.94
resourceCulture
-0.94
SourceChecksum
-0.90
CreateTagHelper
-0.88
CodeAttribute
-0.83
estekak
-0.82
خارجية
-0.82
انيف
-0.81
ChildScrollView
-0.79
esboço
-0.79
POSITIVE LOGITS
|-
1.07
|-
0.77
Garg
0.66
Malte
0.62
|--
0.59
imp
0.59
bord
0.57
Drinks
0.56
centred
0.56
ist
0.56
Activations Density 0.001%