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

    Neuronpedia

    INDEX
    Explanations

    marriage

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of sociodemographic category labels (e.g. marital-status terms like “married,” “single,” “unmarried,” and related demographic descriptors).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     gram
    -0.07
     javascript
    -0.07
    IMO
    -0.06
     проводить
    -0.06
    andon
    -0.06
     。
    -0.06
    _TEM
    -0.06
     Anderson
    -0.06
    -commerce
    -0.06
    _visit
    -0.06
    POSITIVE LOGITS
    .xhtml
    0.07
    ですか
    0.07
    /doc
    0.06
     setDefaultCloseOperation
    0.06
    .constructor
    0.06
     IPT
    0.06
     Geological
    0.06
     impe
    0.06
     numeral
    0.06
     yüz
    0.06
    Act Density 0.004%

    No Known Activations