INDEX

Explanations

aquatic ecosystems and organisms

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

The neuron activates for references to "aquatic" organisms, environments, and ecosystems in scientific text.

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

The neuron is detecting occurrences of the term “aquatic” (i.e. references to aquatic environments, organisms, or systems).

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

 they

-2.41

is

-2.38

袛

-2.36

could

-2.30

 другим

-2.23

在他的

-2.16

os

-2.13

-2.08

—

-2.03

わから

-2.03

POSITIVE LOGITS

ſelves

2.88

 achieve

2.47

 There

2.44

ၞ

2.44

īga

2.42

 acquire

2.31

ၟ

2.31

,\\

2.30

 potreb

2.20

囿

2.20

Activations Density 0.003%

aquatic ecosystems and organisms

The neuron activates for references to "aquatic" organisms, environments, and ecosystems in scientific text.

The neuron is detecting occurrences of the term “aquatic” (i.e. references to aquatic environments, organisms, or systems).

No Comments

No Known Activations

aquatic ecosystems and organisms

The neuron activates for references to "aquatic" organisms, environments, and ecosystems in scientific text.

The neuron is detecting occurrences of the term “aquatic” (i.e. references to aquatic environments, organisms, or systems).

No Comments

No Known Activations