INDEX

Explanations

global warming and emissions

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

content related to climate change, global warming, and greenhouse gases.

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

The neuron primarily detects numeric expressions and quantitative data (e.g. numbers, percentages, and measurements).

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

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_22/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

 infección

-1.33

()]

-1.30

༌

-1.27

他们

-1.26

经常

-1.22

完全

-1.21

億円

-1.20

吸引

-1.19

。

-1.19

 selepas

-1.18

POSITIVE LOGITS

 global

1.55

ಅ

1.43

 worldwide

1.41

ższych

1.40

 today

1.37

 현재

1.30

licante

1.26

ύ

1.26

styrelsen

1.24

 yearly

1.23

Activations Density 0.032%

global warming and emissions

content related to climate change, global warming, and greenhouse gases.

The neuron primarily detects numeric expressions and quantitative data (e.g. numbers, percentages, and measurements).

No Comments

No Known Activations

global warming and emissions

content related to climate change, global warming, and greenhouse gases.

The neuron primarily detects numeric expressions and quantitative data (e.g. numbers, percentages, and measurements).

No Comments

No Known Activations