INDEX
Explanations
The neuron activates on long, multi-part chemical compound names (e.g. “3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide”).
New Auto-Interp
Negative Logits
aza
-0.07
ями
-0.06
_tv
-0.06
حية
-0.06
objet
-0.06
anza
-0.06
trade
-0.06
Boulder
-0.06
зни
-0.06
inds
-0.06
POSITIVE LOGITS
uation
0.07
rencontr
0.06
!!
0.06
!\
0.06
weren
0.06
shaved
0.06
SYN
0.06
xor
0.06
.addChild
0.06
_PORT
0.06
Activations Density 0.005%