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

    Neuronpedia

    INDEX
    Explanations

    Code and web development

    np_max-act · gemini-2.0-flash

    This neuron fires on tokens naming or invoking backend/server‐side code—e.g. language/platform identifiers (PHP, Java, .NET attributes like [HttpPost], WebMethod) or server‐side method/file names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    лет
    -0.09
     hijos
    -0.07
     taco
    -0.07
    生物
    -0.07
    ullet
    -0.06
    }};↵
    -0.06
     bare
    -0.06
    版
    -0.06
    .Selection
    -0.06
     mist
    -0.06
    POSITIVE LOGITS
     evidenced
    0.07
    addElement
    0.06
    自己的
    0.06
     oldukça
    0.06
     itemList
    0.06
     eius
    0.06
     disadv
    0.06
    [${
    0.06
     pří
    0.06
    aceut
    0.06
    Act Density 0.031%

    No Known Activations