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

    Neuronpedia

    INDEX
    Explanations

    websites

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of fan‐site or website branding (e.g. “___ Online,” “Vault,” “fansite,” “website”) in page headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _comb
    -0.06
    /payment
    -0.06
    ************************************************
    -0.06
    _notify
    -0.06
    ocus
    -0.06
    ورة
    -0.06
    -dis
    -0.06
    _words
    -0.06
    KNOWN
    -0.06
     Wine
    -0.06
    POSITIVE LOGITS
     LLVM
    0.07
    iddet
    0.07
    InstanceOf
    0.06
     november
    0.06
     transports
    0.06
    áy
    0.06
     ngoài
    0.06
     hangi
    0.06
    gcd
    0.06
    .HTML
    0.06
    Act Density 0.022%

    No Known Activations