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

    Neuronpedia

    INDEX
    Explanations

    patents

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the word “discloses” (often split into “disc” + “loses”) in patent‐style reference passages.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _msgs
    -0.07
     Phone
    -0.06
     AZ
    -0.06
     сов
    -0.06
    955
    -0.06
     curious
    -0.06
    ?type
    -0.06
    _PROP
    -0.06
    _DIV
    -0.06
     incomplete
    -0.06
    POSITIVE LOGITS
    uguay
    0.07
    Station
    0.07
    essoa
    0.07
    će
    0.07
    (MethodImplOptions
    0.07
    nze
    0.06
     섬
    0.06
    프로
    0.06
    ٬
    0.06
     ニ
    0.06
    Act Density 0.011%

    No Known Activations