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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash

    This neuron fires on code tokens that look like variable or identifier names (especially snake_case names) in programming contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Both
    -0.07
     passionate
    -0.07
     mocker
    -0.06
    uploads
    -0.06
    	no
    -0.06
     soul
    -0.06
     Fur
    -0.06
     enjoy
    -0.06
     Missouri
    -0.06
     plays
    -0.06
    POSITIVE LOGITS
    _Class
    0.07
    .subscription
    0.07
    )o
    0.06
    /course
    0.06
     گزارش
    0.06
    Việc
    0.06
     scripture
    0.06
     γλώ
    0.06
     imagen
    0.06
     янва
    0.06
    Act Density 0.057%

    No Known Activations