INDEX

Explanations

cytotoxic drugs and effects

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

The neuron detects the word "cytotoxic" and related terms about cellular toxicity in scientific/medical contexts.

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

The main thing this neuron does is detect the token “cytotoxic” (and its variants like “cytotoxicity”).

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

曁

-2.05

 colloquial

-1.99

 bäst

-1.98

So

-1.96

Initially

-1.91

黻

-1.91

其他

-1.89

As

-1.89

釭

-1.88

</i>

-1.87

POSITIVE LOGITS

2.14

2.11

蔸

1.99



1.98

and

1.81

蔼

1.78

 avait

1.77

౨

1.77

ਗ਼

1.75

Activations Density 0.025%

cytotoxic drugs and effects

The neuron detects the word "cytotoxic" and related terms about cellular toxicity in scientific/medical contexts.

The main thing this neuron does is detect the token “cytotoxic” (and its variants like “cytotoxicity”).

No Comments

No Known Activations

cytotoxic drugs and effects

The neuron detects the word "cytotoxic" and related terms about cellular toxicity in scientific/medical contexts.

The main thing this neuron does is detect the token “cytotoxic” (and its variants like “cytotoxicity”).

No Comments

No Known Activations