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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act · gemini-2.0-flash

    This neuron activates on HTML/XML tag attribute–value pairs (i.e. the attribute names, equals signs, and quoted attribute values inside markup tags).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -dev
    -0.07
    Insert
    -0.06
     styleUrls
    -0.06
     dzi
    -0.06
    sales
    -0.06
     SWAT
    -0.06
    ativity
    -0.06
    matched
    -0.06
     Sum
    -0.06
     Welt
    -0.06
    POSITIVE LOGITS
     début
    0.06
    стер
    0.06
    umbledore
    0.06
    /facebook
    0.06
    enum
    0.06
     dern
    0.06
    .custom
    0.06
    .Fetch
    0.06
    FIG
    0.06
    $instance
    0.06
    Act Density 0.010%

    No Known Activations