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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron detects legal case citations in the text (e.g. reporter abbreviations like “S.W.” or “S.W.2d” with their volume and page numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -REAL
    -0.07
    _REPEAT
    -0.07
    burgh
    -0.06
    Montserrat
    -0.06
    ニニ
    -0.06
    ewan
    -0.06
    ayıp
    -0.06
     linh
    -0.06
    Subset
    -0.06
    tiles
    -0.06
    POSITIVE LOGITS
     Pero
    0.06
     agre
    0.06
     ürün
    0.06
     bow
    0.06
    éro
    0.06
    bol
    0.06
    ″
    0.06
     condiciones
    0.06
    basePath
    0.06
     fluctuations
    0.06
    Act Density 0.001%

    No Known Activations