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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash

    This neuron detects organization or publisher names written with a slash—e.g. publisher imprints or institutional affiliations formatted like “DC Comics/Vertigo.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ibli
    -0.07
    (Pos
    -0.07
    將
    -0.07
     mill
    -0.07
    新闻
    -0.06
     sip
    -0.06
    _find
    -0.06
     invites
    -0.06
    منت
    -0.06
    illez
    -0.06
    POSITIVE LOGITS
    nder
    0.06
    -global
    0.06
    ?>/
    0.06
    onitor
    0.06
    omanip
    0.06
     Grupo
    0.06
    fell
    0.06
    ']=="
    0.06
     çocuk
    0.06
     ['$
    0.06
    Act Density 0.018%

    No Known Activations