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

    Neuronpedia

    INDEX
    Explanations

    HTML code

    np_max-act · gemini-2.0-flash

    This neuron activates on HTML markup tokens—specifically element names and identifiers (e.g. tag names like “div,” “header,” “footer,” or IDs/classes) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ropes
    -0.06
     Analyzer
    -0.06
     paved
    -0.06
    アー
    -0.06
     cor
    -0.06
     пля
    -0.06
    (ver
    -0.06
    imbledon
    -0.06
     airst
    -0.05
     psychologist
    -0.05
    POSITIVE LOGITS
     differentiated
    0.07
    幸
    0.07
    evin
    0.07
    _spi
    0.07
    .BOLD
    0.07
     withdrawals
    0.07
    '}).
    0.07
    .UnitTesting
    0.07
    .gsub
    0.06
    jev
    0.06
    Act Density 0.034%

    No Known Activations