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

    Neuronpedia

    INDEX
    Explanations

    decorator

    np_max-act · gemini-2.0-flash

    This neuron detects references to “decorator” or decoration metadata (e.g. tokens like Decorate, decorator, experimentalDecorators, emitDecoratorMetadata).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     setInput
    -0.08
    odef
    -0.07
     aun
    -0.07
    -sample
    -0.07
    fds
    -0.06
    stime
    -0.06
     arma
    -0.06
    _text
    -0.06
    kids
    -0.06
    올
    -0.06
    POSITIVE LOGITS
     decorator
    0.09
    Decorator
    0.07
     Purch
    0.06
    isseur
    0.06
     Saskatchewan
    0.06
    Decor
    0.06
     dan
    0.06
    σιμοποι
    0.06
     standing
    0.06
     APPLE
    0.06
    Act Density 0.001%

    No Known Activations