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

    Neuronpedia

    INDEX
    Explanations

    endowments, awards, scholarships

    np_max-act · gemini-2.0-flash

    This neuron detects proper names of donors or benefactors (i.e. named individual sponsors or endowments).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Ih
    -0.07
     Eating
    -0.06
     negotiate
    -0.06
     Psychiat
    -0.06
    Ln
    -0.06
     ώ
    -0.06
    Capture
    -0.06
     FW
    -0.06
    _yield
    -0.06
    strong
    -0.06
    POSITIVE LOGITS
    #
    0.07
    Mountain
    0.07
     kısa
    0.06
    raid
    0.06
     Ranked
    0.06
    calendar
    0.06
     mec
    0.06
     QWidget
    0.06
    anos
    0.06
    Professor
    0.06
    Act Density 0.019%

    No Known Activations