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

    Neuronpedia

    INDEX
    Explanations

    /E

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens—especially decimal numbers and symbols—in financial metrics (e.g. P/E ratios and other valuation figures).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ترل
    -0.07
    ContentLoaded
    -0.07
    Mb
    -0.06
    وی
    -0.06
     pixmap
    -0.06
    сию
    -0.06
    activex
    -0.06
    owered
    -0.06
    унк
    -0.06
    718
    -0.06
    POSITIVE LOGITS
    Davis
    0.08
     Davis
    0.07
    !!!
    0.07
     ''),↵
    0.07
     Campaign
    0.07
     organizace
    0.06
     Elevated
    0.06
     Coupons
    0.06
    -fields
    0.06
     xAxis
    0.06
    Act Density 0.004%

    No Known Activations