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

    Neuronpedia

    INDEX
    Explanations

    async

    np_max-act · gemini-2.0-flash

    This neuron detects Python’s asynchronous programming constructs, especially the “async” and “await” keywords (e.g. `async`, `await`, `asyncio`).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _pb
    -0.07
    bdb
    -0.07
     bio
    -0.06
     Μπ
    -0.06
    iner
    -0.06
    Button
    -0.06
    .jpg
    -0.06
    -handler
    -0.06
    mb
    -0.06
    נ
    -0.06
    POSITIVE LOGITS
     greatly
    0.07
     caval
    0.06
     mastur
    0.06
     Compiled
    0.06
    _seat
    0.06
     assort
    0.06
    рон
    0.06
    になって
    0.06
    раст
    0.06
    θεια
    0.06
    Act Density 0.003%

    No Known Activations