INDEX
Explanations
This neuron responds to mentions of advertisements or advertising in the text.
New Auto-Interp
Negative Logits
wander
-0.06
.eql
-0.06
(("-0.06
tember
-0.06
眠
-0.06
può
-0.06
maxY
-0.06
)}"↵
-0.06
])]↵
-0.06
kemiz
-0.06
POSITIVE LOGITS
-desc
0.07
Ads
0.07
ads
0.07
.removeClass
0.07
gly
0.06
_ENSURE
0.06
.XPATH
0.06
lashes
0.06
L
0.06
RD
0.06
Activations Density 0.010%