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

    Neuronpedia

    INDEX
    Explanations

    DOIs and URLs

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on DOI reference fragments—tokens that form the “dx.doi.org/10.xxxx/…” parts of citation URLs.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    TYPE
    -0.07
    XE
    -0.06
    [C
    -0.06
     Při
    -0.06
    ------+------+
    -0.06
    +A
    -0.06
    externalActionCode
    -0.06
    avras
    -0.06
     lục
    -0.06
     indispensable
    -0.06
    POSITIVE LOGITS
    แผน
    0.07
    QUIRES
    0.07
     자료
    0.06
    _CENTER
    0.06
    .Scanner
    0.06
    .Mobile
    0.06
    icter
    0.06
    avel
    0.06
    >//
    0.06
    .servers
    0.06
    Act Density 0.000%

    No Known Activations