INDEX

Explanations

computer viruses and antivirus programs

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

computer security-related terms, especially "antivirus" and "virus" software references.

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

The neuron activates on words related to computer‐security threats and protections—especially “virus,” “antivirus,” and similar malware/security terms.

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

рода

-1.38

ם

-1.34

 даже

-1.31

 bawah

-1.30

to

-1.30

 ayudará

-1.27

ом

-1.24

<0xD4>

-1.24

sı

-1.24

rinology

-1.21

POSITIVE LOGITS

 dlaczego

1.40

le

1.36

autres

1.32

︲

1.30

说不定

1.30

何度

1.29

1.27

屃

1.27

争取

1.24

에도

1.24

Activations Density 0.016%

computer viruses and antivirus programs

computer security-related terms, especially "antivirus" and "virus" software references.

The neuron activates on words related to computer‐security threats and protections—especially “virus,” “antivirus,” and similar malware/security terms.

No Comments

No Known Activations

computer viruses and antivirus programs

computer security-related terms, especially "antivirus" and "virus" software references.

The neuron activates on words related to computer‐security threats and protections—especially “virus,” “antivirus,” and similar malware/security terms.

No Comments

No Known Activations