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

    Neuronpedia

    INDEX
    Explanations

    scientific publications

    np_max-act · gemini-2.0-flash

    This neuron detects in‐text citation/reference markers (e.g. bracketed citation keys like [@…], “e.g.” abbreviations, section numbers) in academic‐style writing.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     إد
    -0.07
    _round
    -0.06
     chút
    -0.06
     chores
    -0.06
     الرياض
    -0.06
     Роз
    -0.06
    Founded
    -0.06
    their
    -0.06
     alignments
    -0.06
     beverages
    -0.06
    POSITIVE LOGITS
     tabIndex
    0.07
    Header
    0.07
     liber
    0.07
    ’est
    0.07
    _result
    0.06
     durumunda
    0.06
    ZA
    0.06
     vive
    0.06
    (master
    0.06
    '];
    0.06
    Act Density 0.097%

    No Known Activations