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

    Neuronpedia

    INDEX
    Explanations

    math and programming

    np_max-act · gemini-2.0-flash

    This neuron detects LaTeX‐style mathematical notation, especially field symbols (e.g. “\mathbb{F},” “\mathbb{R},” “\mathbb{C}”) and other inline math tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Cr
    -0.07
    ouz
    -0.07
    يان
    -0.07
    uD
    -0.06
    anta
    -0.06
     sushi
    -0.06
     Picker
    -0.06
     fanatic
    -0.06
    ि�
    -0.06
    ومات
    -0.06
    POSITIVE LOGITS
     Shops
    0.08
    <Pair
    0.07
     《
    0.06
     фін
    0.06
     stringstream
    0.06
     JSName
    0.06
     NAMES
    0.06
     itemprop
    0.06
    _eval
    0.06
     wxT
    0.06
    Act Density 0.036%

    No Known Activations