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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron activates specifically on numerical tokens and numeric expressions (digits, percentages, and numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _format
    -0.06
    ло
    -0.06
    기로
    -0.06
    surface
    -0.06
     module
    -0.06
     basePath
    -0.06
    _based
    -0.06
    django
    -0.06
    剑
    -0.06
    ير
    -0.06
    POSITIVE LOGITS
    특별시
    0.06
     ''↵
    0.06
    _MetaData
    0.06
     Федераль
    0.06
    ").↵
    0.06
    =''↵
    0.06
    )')↵
    0.06
    ικη
    0.06
     süt
    0.06
    _batches
    0.06
    Act Density 0.031%

    No Known Activations