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

    Neuronpedia

    INDEX
    Explanations

    Code and programming

    np_max-act · gemini-2.0-flash

    This neuron activates on CamelCase identifiers (e.g. method or class names) in source code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Bei
    -0.07
    adders
    -0.07
     Bite
    -0.06
     розмі
    -0.06
    >alert
    -0.06
    _wo
    -0.06
    ，就是
    -0.06
     продаж
    -0.06
    \htdocs
    -0.06
    .SubElement
    -0.06
    POSITIVE LOGITS
    ."'
    0.07
     Psalm
    0.06
     suppress
    0.06
     Industry
    0.06
    ?????
    0.06
     spine
    0.06
     unified
    0.06
    Unload
    0.06
     streamline
    0.06
    uchen
    0.06
    Act Density 0.116%

    No Known Activations