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

    Neuronpedia

    INDEX
    Explanations

    code, lists, formulas

    np_max-act · gemini-2.0-flash

    The neuron consistently lights up on numeric tokens containing decimal points (i.e. floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    living
    -0.06
    บาย
    -0.06
     apprentice
    -0.06
    継
    -0.06
     bulky
    -0.06
     DbType
    -0.06
    ListOf
    -0.06
    explicit
    -0.06
     因
    -0.06
     Param
    -0.06
    POSITIVE LOGITS
     ك
    0.07
     Он
    0.07
     ApiException
    0.07
     Organisation
    0.07
     更
    0.07
    GetObject
    0.06
    .dex
    0.06
    更
    0.06
    化学
    0.06
     Ör
    0.06
    Act Density 0.256%

    No Known Activations