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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron fires on multi‐line comment headers—especially licensing and copyright boilerplate at the top of source files.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     moss
    -0.07
     dřev
    -0.07
    .fxml
    -0.06
    IDGE
    -0.06
    locs
    -0.06
    dfd
    -0.06
     stranded
    -0.06
     藤
    -0.06
    apGestureRecognizer
    -0.06
    equiv
    -0.06
    POSITIVE LOGITS
     бюдж
    0.08
    ＝＝
    0.06
    expenses
    0.06
    вий
    0.06
    ++++++++++++++++++++++++++++++++
    0.06
     bridal
    0.06
     Liste
    0.06
     reelection
    0.06
    ++++++++++++++++
    0.06
    Generally
    0.06
    Act Density 0.028%

    No Known Activations