INDEX

Explanations

aqua, aquarius, aquaman, aquaporins

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

The neuron detects proper nouns containing "aqua" or water-related terms like "aquarium" and "aquaman".

oai_token-act-pair · claude-3-7-sonnet-20250219 Triggered by @neilrathi

The neuron activates on any token containing the substring “aqu” (e.g. “Aqua,” “aquarium,” “aquaporins,” etc.).

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

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_10/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

which

-2.47

-2.09

需要

-2.09

 esperienza

-2.08

ться

-2.05

 lame

-1.98

きちんと

-1.98

仅仅

-1.96

 copertina

-1.95

 inaweza

-1.95

POSITIVE LOGITS

朦

2.42

 剧照

2.19

腿

2.13

鍇

2.08

瑒

2.06

 delve

2.05

沨

2.05

﹅

2.03

嵛

1.97

Disappear

1.96

Activations Density 0.007%

aqua, aquarius, aquaman, aquaporins

The neuron detects proper nouns containing "aqua" or water-related terms like "aquarium" and "aquaman".

The neuron activates on any token containing the substring “aqu” (e.g. “Aqua,” “aquarium,” “aquaporins,” etc.).

No Comments

No Known Activations

aqua, aquarius, aquaman, aquaporins

The neuron detects proper nouns containing "aqua" or water-related terms like "aquarium" and "aquaman".

The neuron activates on any token containing the substring “aqu” (e.g. “Aqua,” “aquarium,” “aquaporins,” etc.).

No Comments

No Known Activations