INDEX

Explanations

cortisol and cancel actions

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

This neuron detects the word "cortisol" in medical/scientific contexts and "Cancel" in programming/interface contexts.

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

The neuron fires most strongly on occurrences of the hormone name “cortisol” when it’s paired with a numeric value, i.e. cortisol level measurements.

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

But

-2.42

 简约

-2.31

äjä

-2.19

 复古

-2.19

ременно

-2.19

 inoltre

-2.19

 Перейти

-2.17

眎

-2.17

-2.16

桌

-2.14

POSITIVE LOGITS

↵↵

3.16

3.09

2.92

⢫

2.39

2.38

י

2.30

蓑

2.23

 возле

2.22

erda

2.22

''

2.22

Activations Density 0.007%

cortisol and cancel actions

This neuron detects the word "cortisol" in medical/scientific contexts and "Cancel" in programming/interface contexts.

The neuron fires most strongly on occurrences of the hormone name “cortisol” when it’s paired with a numeric value, i.e. cortisol level measurements.

No Comments

No Known Activations

cortisol and cancel actions

This neuron detects the word "cortisol" in medical/scientific contexts and "Cancel" in programming/interface contexts.

The neuron fires most strongly on occurrences of the hormone name “cortisol” when it’s paired with a numeric value, i.e. cortisol level measurements.

No Comments

No Known Activations