INDEX

Explanations

covid coronavirus pandemic

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

phrases describing challenges, disruptions, or negative situations, particularly those caused by external events or circumstances.

oai_token-act-pair · claude-3-7-sonnet-20250219

Triggered by @neilrathi

The neuron fires on words and short phrases that serve as temporal or narrative transition cues (e.g., dates, adverbs like “Shortly,” “Now,” and time-sequence connectors).

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

Negative Logits

 lento

-0.94

褲

-0.93

sses

-0.90

 decy

-0.90

 llamaba

-0.90

っていない

-0.88

UNDLE

-0.86

Dich

-0.85

 herido

-0.85

FILM

-0.85

POSITIVE LOGITS

 Covid

1.64

 COVID

1.59

 coronavirus

1.45

 recent

1.29

 covid

1.23

COVID

1.21

 Coronavirus

1.10

 Corona

1.08

Covid

1.02

 corona

1.01

Activations Density 0.062%

covid coronavirus pandemic

phrases describing challenges, disruptions, or negative situations, particularly those caused by external events or circumstances.

The neuron fires on words and short phrases that serve as temporal or narrative transition cues (e.g., dates, adverbs like “Shortly,” “Now,” and time-sequence connectors).

No Known Activations

covid coronavirus pandemic

phrases describing challenges, disruptions, or negative situations, particularly those caused by external events or circumstances.

The neuron fires on words and short phrases that serve as temporal or narrative transition cues (e.g., dates, adverbs like “Shortly,” “Now,” and time-sequence connectors).

No Known Activations