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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash

    This neuron responds to typographic opening quotation marks (e.g. “).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     bei
    -0.07
     paramMap
    -0.07
     tiện
    -0.06
    服務
    -0.06
     ilişkin
    -0.06
     Browser
    -0.06
    (suffix
    -0.06
     dès
    -0.06
    ispiel
    -0.06
    Hamilton
    -0.06
    POSITIVE LOGITS
     فت
    0.07
     ann
    0.06
     Кри
    0.06
    Unary
    0.06
     tyranny
    0.06
     beau
    0.06
     indigenous
    0.06
    ψη
    0.06
    zhou
    0.06
     Offset
    0.06
    Act Density 0.041%

    No Known Activations