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

    Neuronpedia

    INDEX
    Explanations

    file extensions

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens belonging to link‐markup and navigation elements—such as Markdown link brackets, parentheses, file names (e.g. .md, .html), URLs, and “Back to…” navigation phrases.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Tire
    -0.06
    除了
    -0.06
    B
    -0.06
    (_('
    -0.06
    還
    -0.06
    .nz
    -0.06
     SQL
    -0.06
    点
    -0.06
    -ar
    -0.06
    Servers
    -0.06
    POSITIVE LOGITS
    lict
    0.08
     γρα
    0.07
    azen
    0.07
    ificate
    0.07
     quieres
    0.06
    ất
    0.06
    spir
    0.06
    built
    0.06
    ากล
    0.06
    _GOOD
    0.06
    Act Density 0.009%

    No Known Activations