INDEX

Explanations

outside of

np_acts-logits-general · gemini-2.5-flash-lite

The neuron fires on occurrences of the word “outside” (particularly in phrases like “outside the/of”).

oai_token-act-pair · o4-mini Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_34/width_131k

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

selbe

-1.09

 печени

-1.08

 кілька

-1.05

ísimas

-1.02

 combustível

-1.01

 Tonnen

-1.00

 внутріш

-1.00

つて

-1.00

 ويت

-0.94

 Könige

-0.94

POSITIVE LOGITS

of

5.00

the

1.85

ркут

1.23

 gruppe

1.17

zehnten

1.09

 arvio

1.08

 Tyskland

1.07

чего

1.07

ของ

1.05

$>$

1.03

Activations Density 0.013%

outside of

The neuron fires on occurrences of the word “outside” (particularly in phrases like “outside the/of”).

No Comments

No Known Activations

outside of

The neuron fires on occurrences of the word “outside” (particularly in phrases like “outside the/of”).

No Comments

No Known Activations

outside of

The neuron fires on occurrences of the word “outside” (particularly in phrases like “outside the/​of”).

No Comments

No Known Activations

outside of

The neuron fires on occurrences of the word “outside” (particularly in phrases like “outside the/​of”).

No Comments

No Known Activations

The neuron fires on occurrences of the word “outside” (particularly in phrases like “outside the/of”).

The neuron fires on occurrences of the word “outside” (particularly in phrases like “outside the/of”).