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

    Neuronpedia

    INDEX
    Explanations

    special

    np_max-act · gemini-2.0-flash

    This neuron identifies explanations of “special characters” (i.e. tokens that need escaping) in command-or‐regex syntax.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    compact
    -0.06
    Ｄ
    -0.06
     석
    -0.06
    虽然
    -0.06
    ALLEL
    -0.06
    마다
    -0.06
    .mem
    -0.06
     žádné
    -0.06
     Superman
    -0.06
     انجمن
    -0.06
    POSITIVE LOGITS
    toBeInTheDocument
    0.07
    (android
    0.07
    �
    0.06
    vous
    0.06
    .od
    0.06
    alerts
    0.06
     wear
    0.06
    .abs
    0.06
     reachable
    0.06
    challenge
    0.06
    Act Density 0.014%

    No Known Activations