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

    Neuronpedia

    INDEX
    Explanations

    /web

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that are parts of web archive URLs (e.g. “web.archive.org/web” and associated numeric path segments).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     hat
    -0.07
     contradict
    -0.07
    irá
    -0.06
     costly
    -0.06
     dames
    -0.06
     Stadt
    -0.06
    psc
    -0.06
    _ASC
    -0.06
     São
    -0.06
     playerName
    -0.06
    POSITIVE LOGITS
     uyum
    0.07
    :^
    0.06
    Decorator
    0.06
    MainActivity
    0.06
     Student
    0.06
    /web
    0.06
     Rainbow
    0.06
     Thông
    0.06
    ا�
    0.06
    OutOfBounds
    0.06
    Act Density 0.000%

    No Known Activations