INDEX
Explanations
attributes related to Android UI components and their configurations
New Auto-Interp
Negative Logits
owie
-0.17
ascar
-0.16
ertz
-0.15
.ng
-0.15
ppo
-0.15
ÑĤал
-0.15
Ware
-0.15
allis
-0.14
airo
-0.14
akh
-0.14
POSITIVE LOGITS
ocs
0.14
GEST
0.14
atype
0.14
Jacobs
0.13
orderby
0.13
Queryable
0.13
tle
0.13
ovna
0.13
kea
0.13
rier
0.13
Activations Density 0.013%