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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash

    This neuron activates on HTML markup—specifically tokens inside tags such as attribute names, equals signs, quoted values, and class/grid-name tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    金属
    -0.07
    411
    -0.07
     Samar
    -0.06
    yan
    -0.06
     seals
    -0.06
     sendMessage
    -0.06
    истра
    -0.06
     significa
    -0.06
     menn
    -0.06
    655
    -0.06
    POSITIVE LOGITS
    ",
↵
    0.07
    .removeClass
    0.07
    SuppressWarnings
    0.06
    .MapFrom
    0.06
     vetor
    0.06
    Autoresizing
    0.06
    )$_
    0.06
    (#)
    0.06
       ↵
    0.06
    	Check
    0.06
    Act Density 0.006%

    No Known Activations