Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    less than sign

    np_max-act · gemini-2.0-flash

    The neuron is primarily detecting HTML markup tokens, especially opening `<div>` tags.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     dùng
    -0.07
    ileri
    -0.07
    bia
    -0.06
     detr
    -0.06
     �
    -0.06
    Dic
    -0.06
    대비
    -0.06
    つぶ
    -0.06
     미
    -0.06
     rendering
    -0.06
    POSITIVE LOGITS
     हत
    0.07
     Duncan
    0.06
     LoginForm
    0.06
    protected
    0.06
    -goal
    0.06
    .Files
    0.06
    .labelControl
    0.06
    명의
    0.06
     situation
    0.06
    800
    0.06
    Act Density 0.007%

    No Known Activations