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

    Neuronpedia

    INDEX
    Explanations

    used

    np_max-act · gemini-2.0-flash

    This neuron detects patent‐style definitional boilerplate, specifically phrases like “As used herein, the term … refers to ….” that introduce formal definitions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    technical terms related to microelectromechanical systems (MEMS) and their functions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     nejen
    -0.07
    Tem
    -0.07
    ýv
    -0.06
    /payment
    -0.06
    ovní
    -0.06
     Et
    -0.06
     Kits
    -0.06
     Evropské
    -0.06
    EMPLARY
    -0.06
    ieving
    -0.06
    POSITIVE LOGITS
     années
    0.07
    (strcmp
    0.07
     життя
    0.06
    特色
    0.06
    (mean
    0.06
     статті
    0.06
     navbar
    0.06
     zusammen
    0.06
    責
    0.06
     después
    0.06
    Act Density 0.009%

    No Known Activations