INDEX
Explanations
The neuron activates on occurrences of the word “nerve” (and its close variants) in biomedical text.
New Auto-Interp
Negative Logits
emony
-0.08
Національ
-0.07
icted
-0.07
(box
-0.07
Ó
-0.07
abox
-0.07
gui
-0.07
ITHER
-0.06
XL
-0.06
↵↵
-0.06
POSITIVE LOGITS
nerve
0.13
nerves
0.11
ren
0.07
injuries
0.07
令人
0.07
erve
0.07
рев
0.07
Dave
0.07
erv
0.07
pulse
0.07
Activations Density 0.004%