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

    Neuronpedia

    INDEX
    Explanations

    browser

    np_max-act · gemini-2.0-flash

    This neuron activates on instructions to open or use a web browser (e.g., “Abra um navegador web e navegue até …”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ựa
    -0.07
    SCALL
    -0.07
    (value
    -0.06
     compatibility
    -0.06
    VERR
    -0.06
    .command
    -0.06
     elastic
    -0.06
    冠
    -0.06
    currentIndex
    -0.06
    ệnh
    -0.06
    POSITIVE LOGITS
    џN
    0.07
    [$_
    0.06
    .TH
    0.06
    idf
    0.06
    .shopping
    0.06
     Baş
    0.06
    while
    0.06
    	Vec
    0.06
    getPath
    0.06
    ?><
    0.06
    Act Density 0.010%

    No Known Activations