INDEX

Explanations

petroleum, gasoline, and oil extraction

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

references to petroleum products like oil, gas, gasoline, and fuel.

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

The neuron activates on words referring to petroleum-derived fuels and related petrochemical products.

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

 varför

-1.27

","

-1.25

—

-1.23

");

-1.22

">

-1.21

‘

-1.17

瞪

-1.16

February

-1.10

 estas

-1.09

ertia

-1.09

POSITIVE LOGITS

oil

1.99

 fuel

1.77

 minyak

1.29

 benzin

1.22

 petróleo

1.21

 fuels

1.21

⁕

1.21

赚

1.18

 Fuel

1.17

accéder

1.17

Activations Density 0.063%

petroleum, gasoline, and oil extraction

references to petroleum products like oil, gas, gasoline, and fuel.

The neuron activates on words referring to petroleum-derived fuels and related petrochemical products.

No Comments

No Known Activations

petroleum, gasoline, and oil extraction

references to petroleum products like oil, gas, gasoline, and fuel.

The neuron activates on words referring to petroleum-derived fuels and related petrochemical products.

No Comments

No Known Activations