INDEX

Explanations

AWS infrastructure and services

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

This neuron detects the hidden byte‐order‐mark (zero-width) characters (often shown as “”) that precede text.

oai_token-act-pair · o4-mini Triggered by @jyhe0408

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

Not in Any Lists

No Comments

Negative Logits

Př

0.76

하라

0.73

ਜ਼

0.71

 いう

0.71

 ebay

0.70

 ইয়াহিয়ার

0.68

 google

0.67

}},\

0.66

ㅛ

0.66

tł

0.65

POSITIVE LOGITS

्रा

0.75

खिल

0.75

ajana

0.72

($"{

0.71

riffe

0.70

produksi

0.70

ivis

0.69

 spearheaded

0.68

lage

0.68

laš

0.67

Activations Density 0.022%

AWS infrastructure and services

This neuron detects the hidden byte‐order‐mark (zero-width) characters (often shown as “”) that precede text.

No Comments

No Known Activations

AWS infrastructure and services

This neuron detects the hidden byte‐order‐mark (zero-width) characters (often shown as “”) that precede text.

No Comments

No Known Activations

AWS infrastructure and services

This neuron detects the hidden byte‐order‐mark (zero-width) characters (often shown as “﻿”) that precede text.

No Comments

No Known Activations

AWS infrastructure and services

This neuron detects the hidden byte‐order‐mark (zero-width) characters (often shown as “﻿”) that precede text.

No Comments

No Known Activations

This neuron detects the hidden byte‐order‐mark (zero-width) characters (often shown as “”) that precede text.

This neuron detects the hidden byte‐order‐mark (zero-width) characters (often shown as “”) that precede text.