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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash

    text related to programming code, specifically focusing on header files, licensing details, and function definitions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on the standard file‐header/license boilerplate (e.g. copyright notices and license comments) at the top of source files.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     můž
    -0.07
    .utility
    -0.07
    _arc
    -0.07
     heroin
    -0.07
     snapchat
    -0.07
     shine
    -0.06
    ीफ
    -0.06
    fos
    -0.06
     gratuit
    -0.06
    рупп
    -0.06
    POSITIVE LOGITS
    osci
    0.07
    ogle
    0.07
     padr
    0.07
    Australia
    0.07
     siz
    0.06
    actic
    0.06
    autoload
    0.06
    ательно
    0.06
    роиз
    0.06
     activeClassName
    0.06
    Act Density 0.126%

    No Known Activations