INDEX

Explanations

bioinformatics and informatics

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

terms related to the field of "informatics," particularly as it appears in scientific and academic contexts.

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

The neuron activates on mentions of “informatics” (and its sub‐parts like “informat,” “informatic,” etc.) in domain names (e.g. medical informatics, bioinformatics).

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

?"

-2.52

 ominous

-2.11

ются

-2.08

\{

-2.08

ون

-2.06

ี

-2.06

am

-1.99

ti

-1.98

是啊

-1.98

𝘕

-1.97

POSITIVE LOGITS

︲

2.50

にします

2.34

なければ

2.33

 để

2.31

鱟

2.28

 регионе

2.25

 untuk

2.20

怎么能

2.19

霎

2.11

？）

2.08

Activations Density 0.006%

bioinformatics and informatics

terms related to the field of "informatics," particularly as it appears in scientific and academic contexts.

The neuron activates on mentions of “informatics” (and its sub‐parts like “informat,” “informatic,” etc.) in domain names (e.g. medical informatics, bioinformatics).

No Comments

No Known Activations

bioinformatics and informatics

terms related to the field of "informatics," particularly as it appears in scientific and academic contexts.

The neuron activates on mentions of “informatics” (and its sub‐parts like “informat,” “informatic,” etc.) in domain names (e.g. medical informatics, bioinformatics).

No Comments

No Known Activations