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

    Neuronpedia

    INDEX
    Explanations

    single quote

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literals (digits and numbers, including integers and decimals) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     rectangles
    -0.07
    Ing
    -0.07
     подход
    -0.07
    doc
    -0.07
     �
    -0.06
     разд
    -0.06
    peare
    -0.06
    "',
    -0.06
    难
    -0.06
    $req
    -0.06
    POSITIVE LOGITS
    .DataVisualization
    0.07
     Bảo
    0.06
    .executeQuery
    0.06
    _preds
    0.06
    jing
    0.06
     collaboration
    0.06
    _money
    0.06
    .split
    0.06
    _equiv
    0.06
    ob
    0.06
    Act Density 0.012%

    No Known Activations