INDEX
Explanations
references to legal or regulatory statements
New Auto-Interp
Negative Logits
other
-0.54
other
-0.53
Andere
-0.51
Autres
-0.50
Other
-0.49
Andere
-0.49
Other
-0.48
Nieren
-0.48
similarly
-0.47
Umum
-0.47
POSITIVE LOGITS
FetchType
0.69
tagHelperRunner
0.66
awtextra
0.65
endpush
0.62
AndEndTag
0.59
adpleegd
0.58
disambiguazione
0.58
بوابة
0.58
----</
0.56
незавершена
0.56
Activations Density 0.285%