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

    Neuronpedia

    INDEX
    Explanations

    punctuation characters

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on URL and hyperlink components—especially numeric IDs, punctuation, and path tokens in web addresses.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     {[%
    -0.06
     cheating
    -0.06
    ServletRequest
    -0.06
    suggest
    -0.06
     CFR
    -0.06
    .re
    -0.06
     anus
    -0.06
     poured
    -0.06
    Airport
    -0.06
     *----------------------------------------------------------------
    -0.06
    POSITIVE LOGITS
     Files
    0.07
     metodo
    0.07
     continu
    0.07
     highs
    0.07
    whereIn
    0.06
     système
    0.06
    Ao
    0.06
     sentido
    0.06
    اصيل
    0.06
     Мин
    0.06
    Act Density 0.004%

    No Known Activations