INDEX
Explanations
The neuron activates on words appearing in section or subsection headings and titles.
New Auto-Interp
Negative Logits
оград
-0.06
aforementioned
-0.06
ldap
-0.06
Inst
-0.06
Minh
-0.06
factions
-0.06
translateY
-0.06
трьох
-0.06
unrest
-0.06
Beginning
-0.06
POSITIVE LOGITS
sal
0.06
.setBackgroundResource
0.06
rot
0.06
ycling
0.06
Hol
0.06
.skill
0.06
หนอง
0.06
دست
0.06
ROT
0.06
anchors
0.06
Activations Density 0.091%