INDEX

Explanations

proof of work, blocks, coins

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

technical content related to cryptocurrency and blockchain systems.

oai_token-act-pair · claude-4-5-sonnet Triggered by @bfgcn7frf5

The neuron is triggered by technical identifiers and jargon—especially uppercase acronyms, CamelCase names, module or library symbols, protocol constants, and other programming- or domain-specific terms.

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

{~

-1.29

’

-1.26

</td>

-1.26

AND

-1.16

不知道

-1.15

不要

-1.13

");

-1.13

$+$

-1.12

 dergleichen

-1.09

POSITIVE LOGITS

 there

1.36

shaft

1.19

ϐ

1.14

 ersten

1.13

richtig

1.13

anstalt

1.10

്ര

1.09

 Mehrheit

1.09

someone

1.07

 veiligheid

1.06

Activations Density 0.025%

proof of work, blocks, coins

technical content related to cryptocurrency and blockchain systems.

The neuron is triggered by technical identifiers and jargon—especially uppercase acronyms, CamelCase names, module or library symbols, protocol constants, and other programming- or domain-specific terms.

No Comments

No Known Activations

proof of work, blocks, coins

technical content related to cryptocurrency and blockchain systems.

The neuron is triggered by technical identifiers and jargon—especially uppercase acronyms, CamelCase names, module or library symbols, protocol constants, and other programming- or domain-specific terms.

No Comments

No Known Activations