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

    Neuronpedia

    INDEX
    Explanations

    citations

    np_max-act · gemini-2.0-flash

    The neuron detects academic reference or citation markers (e.g., “[”, “@ref”, and numbered reference tags) in scientific text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (driver
    -0.06
    _FRIEND
    -0.06
     Clients
    -0.06
    .textColor
    -0.06
     StartCoroutine
    -0.06
    _crc
    -0.06
    itories
    -0.06
    小学
    -0.06
    agara
    -0.06
     quarterly
    -0.06
    POSITIVE LOGITS
     inspected
    0.06
     작성
    0.06
    õi
    0.06
    itlement
    0.06
     completo
    0.06
    увався
    0.06
     روستا
    0.06
    ляється
    0.06
     capitalized
    0.06
    �
    0.06
    Act Density 0.013%

    No Known Activations