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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash

    This neuron detects patent publication references (e.g. document codes like “A1” following patent numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _ok
    -0.06
    .findIndex
    -0.06
    polygon
    -0.06
    Path
    -0.06
     realization
    -0.06
    .setFill
    -0.06
     pathogens
    -0.06
    Yaw
    -0.06
     آرام
    -0.06
    (sizeof
    -0.06
    POSITIVE LOGITS
     컴
    0.07
     accum
    0.07
     같습니다
    0.06
     εγκα
    0.06
    \"]
    0.06
     сло
    0.06
     uluslararası
    0.06
     gim
    0.06
    xAD
    0.06
     serializer
    0.06
    Act Density 0.001%

    No Known Activations