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

    Neuronpedia

    INDEX
    Explanations

    data structures or APIs

    np_max-act · gemini-2.0-flash

    The neuron fires on programming‐language identifiers written in CamelCase or PascalCase (e.g. type, class, or resource names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     frontend
    -0.07
     Serializable
    -0.06
    řila
    -0.06
    ivent
    -0.06
    ResponseType
    -0.06
    Bitmap
    -0.06
    opup
    -0.06
     Vad
    -0.06
    σφ
    -0.06
     动
    -0.06
    POSITIVE LOGITS
    描
    0.07
     Shorts
    0.06
    _countries
    0.06
    %;">↵
    0.06
    ¸
    0.06
     мн
    0.06
     shrinking
    0.06
    保存
    0.06
    سانی
    0.06
     ‎
    0.06
    Act Density 0.039%

    No Known Activations