INDEX

Explanations

YOLO object detection

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

technical terms and proper nouns related to neural networks, computer vision, and machine learning frameworks (like YOLO, MobileNet, darknet, Caffe).

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

The main thing this neuron does is detect mentions of specific neural network model names and version identifiers (e.g. “YOLO v3,” “Darknet,” “MobileNet,” “Caffe”).

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

-1.59

 creature

-1.41

↵

-1.35

$=

-1.30

「

-1.29

『

-1.24

 Homem

-1.23

ſſen

-1.23

誰

-1.22

学校の

-1.20

POSITIVE LOGITS

’

1.44

 uwag

1.33

Kanal

1.27

منم

1.24

 RoutedEventArgs

1.20

 reduziert

1.19

鴆

1.17

 medy

1.16

 konsep

1.14

 erhielten

1.13

Activations Density 0.013%

YOLO object detection

technical terms and proper nouns related to neural networks, computer vision, and machine learning frameworks (like YOLO, MobileNet, darknet, Caffe).

The main thing this neuron does is detect mentions of specific neural network model names and version identifiers (e.g. “YOLO v3,” “Darknet,” “MobileNet,” “Caffe”).

No Comments

No Known Activations

YOLO object detection

technical terms and proper nouns related to neural networks, computer vision, and machine learning frameworks (like YOLO, MobileNet, darknet, Caffe).

The main thing this neuron does is detect mentions of specific neural network model names and version identifiers (e.g. “YOLO v3,” “Darknet,” “MobileNet,” “Caffe”).

No Comments

No Known Activations