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

    Neuronpedia

    INDEX
    Explanations

    closing brackets

    np_max-act · gemini-2.0-flash

    This neuron activates on code tokens that refer to accessing or traversing XML/HTML elements (e.g. methods like Element, Elements, getElementsByTagName, Descendants, parse, load).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .grid
    -0.08
    qi
    -0.08
     nhất
    -0.07
    -play
    -0.07
    159
    -0.07
    datas
    -0.07
    -map
    -0.06
    �
    -0.06
    tablet
    -0.06
     cabin
    -0.06
    POSITIVE LOGITS
     dovol
    0.06
     Sloven
    0.06
    .CustomButton
    0.06
    UDO
    0.06
     ölüm
    0.06
    FirstOrDefault
    0.05
     وش
    0.05
     cycl
    0.05
    olicited
    0.05
     helicopters
    0.05
    Act Density 0.017%

    No Known Activations