INDEX

Explanations

historical contexts and past events

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

The neuron responds to passages describing historical or ancient context—mentions of past peoples, eras, places, and events.

oai_token-act-pair · o4-mini

Triggered by @jyhe0408

historical or descriptive passages about ancient civilizations and their peoples, customs, and daily life.

oai_token-act-pair · claude-4-5-sonnet

Triggered by @jrosseruk

New Auto-Interp

Configuration

google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 आहे

1.29

 tiene

1.17

 آهي

1.16

 ہیں

1.16

 आहेत

1.13

 são

1.13

 tengo

1.12

 můžete

1.11

 हैं

1.10

 është

1.10

POSITIVE LOGITS

當時

1.59

当时

1.55

 كانوا

1.53

当时的

1.53

 بودند

1.49

もあった

1.45

 وكانت

1.44

 damals

1.38

那时候

1.38

 avevano

1.37

Activations Density 0.712%

historical contexts and past events

The neuron responds to passages describing historical or ancient context—mentions of past peoples, eras, places, and events.

historical or descriptive passages about ancient civilizations and their peoples, customs, and daily life.

No Known Activations

historical contexts and past events

The neuron responds to passages describing historical or ancient context—mentions of past peoples, eras, places, and events.

historical or descriptive passages about ancient civilizations and their peoples, customs, and daily life.

No Known Activations