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

    Neuronpedia

    INDEX
    Explanations

    generic English text

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric and quantitative tokens—years, percentages, decimal numbers, dates, and other number-like strings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Quản
    -0.06
     sms
    -0.06
    -/
    -0.06
    Kick
    -0.06
    _IL
    -0.06
     suk
    -0.06
     фото
    -0.06
     وال
    -0.06
     abril
    -0.06
    _AP
    -0.06
    POSITIVE LOGITS
     reflecting
    0.06
    ADS
    0.06
     dirt
    0.06
    OCKET
    0.06
    ollipop
    0.06
    ections
    0.06
     revised
    0.06
     lint
    0.06
    published
    0.06
    ToLower
    0.06
    Act Density 0.181%

    No Known Activations