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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the literal HTML paragraph tag name “p” (e.g. in getElementsByTagName('p')).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    show
    -0.07
     bach
    -0.07
     sports
    -0.07
    	show
    -0.07
     spree
    -0.07
     slavery
    -0.07
    _recent
    -0.06
    react
    -0.06
     rodin
    -0.06
    stdio
    -0.06
    POSITIVE LOGITS
    _spot
    0.07
    μο
    0.06
     Electricity
    0.06
     ObjectType
    0.06
     Kick
    0.06
     можлив
    0.06
    роз
    0.06
    pdo
    0.06
     thiệu
    0.06
     некоторые
    0.06
    Act Density 0.020%

    No Known Activations