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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numeric literals (decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Archive
    -0.06
    \ORM
    -0.06
    έρει
    -0.06
    anguage
    -0.06
    อน
    -0.06
     Produ
    -0.06
    TOOLS
    -0.06
    ADA
    -0.06
    Participant
    -0.06
     erotic
    -0.06
    POSITIVE LOGITS
     ldc
    0.07
    (Global
    0.07
     fondo
    0.06
     Colin
    0.06
     Equals
    0.06
     afar
    0.06
    livě
    0.06
    银行
    0.06
    ２０
    0.06
    valor
    0.06
    Act Density 0.030%

    No Known Activations