INDEX
Explanations
mentions of icons or buttons related to user interface elements
New Auto-Interp
Negative Logits
løs
-0.40
מוכ
-0.38
czny
-0.37
findpost
-0.35
RoutingModule
-0.35
municipi
-0.34
vimos
-0.33
ścic
-0.32
jamientos
-0.32
rboles
-0.32
POSITIVE LOGITS
fa
2.31
Fa
1.34
Fa
1.23
fa
1.02
фа
0.98
FA
0.96
glyphicon
0.93
Faw
0.89
FA
0.85
Fai
0.84
Activations Density 0.002%