INDEX

Explanations

RFID and HID technologies

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

the acronym "RFID" (Radio Frequency Identification).

oai_token-act-pair · claude-4-5-sonnet Triggered by @bfgcn7frf5

This neuron detects numeric identifier tokens that immediately follow technical acronyms (e.g. “RFID 172,” “Identification 70.5,” “HID 154”).

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

-5.16

ی

-3.27

呖

-2.58

崙

-2.52

⸰

-2.48

癀

-2.42

了

-2.39

狃

-2.39

🫔

-2.36

衕

-2.33

POSITIVE LOGITS

The

2.98

ではまた

2.70

2.45

 และ

2.33

并将

2.28

 глав

2.16

');

2.16

\\

2.13

 белого

2.13

ᴋ

2.09

Activations Density 0.008%

RFID and HID technologies

the acronym "RFID" (Radio Frequency Identification).

This neuron detects numeric identifier tokens that immediately follow technical acronyms (e.g. “RFID 172,” “Identification 70.5,” “HID 154”).

No Comments

No Known Activations

RFID and HID technologies

the acronym "RFID" (Radio Frequency Identification).

This neuron detects numeric identifier tokens that immediately follow technical acronyms (e.g. “RFID 172,” “Identification 70.5,” “HID 154”).

No Comments

No Known Activations