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

    Neuronpedia

    INDEX
    Explanations

    Chrome or Safari

    np_max-act · gemini-2.0-flash

    The neuron detects tokens that appear in browser User-Agent strings (e.g. “Mozilla,” “Windows NT,” “AppleWebKit,” “Chrome,” “Safari,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     [["
    -0.07
     SA
    -0.07
     Laurie
    -0.07
    UK
    -0.06
     مسئله
    -0.06
    �
    -0.06
    менту
    -0.06
    (ld
    -0.06
     Printf
    -0.06
     validity
    -0.06
    POSITIVE LOGITS
     Carnival
    0.07
    Cargo
    0.06
     petitions
    0.06
    交易
    0.06
    مارات
    0.06
    äß
    0.06
     PCS
    0.06
    pay
    0.06
    .getInt
    0.06
    rait
    0.06
    Act Density 0.001%

    No Known Activations