INDEX
Explanations
this neuron finds place names in China, and words related to medicine
Locations and medicine
New Auto-Interp
Negative Logits
twimg
-0.55
NameInMap
-0.50
InstrumentedTest
-0.45
ItemGroup
-0.42
ervan
-0.41
q
-0.40
v
-0.40
thren
-0.40
programmes
-0.40
против
-0.39
POSITIVE LOGITS
存于互联网档案馆
0.72
DockStyle
0.64
GEBURTS
0.61
//</
0.60
CURIAM
0.59
ModelExpression
0.59
édrale
0.58
dawnictwo
0.57
findpost
0.56
WQS
0.56
Activations Density 1.244%