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 citations of patent publications (e.g. “Kokai Unexamined Patent Publication No. …”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Driver
    -0.07
     Clim
    -0.06
    (Self
    -0.06
    ใหม
    -0.06
    _scene
    -0.06
    _study
    -0.06
     पर
    -0.06
     anal
    -0.06
    nodiscard
    -0.06
     yaşan
    -0.06
    POSITIVE LOGITS
     cj
    0.08
     nhật
    0.06
     طبي
    0.06
    olini
    0.06
    _ATTRIBUTE
    0.06
     controversial
    0.06
     Thị
    0.06
     enhance
    0.06
     νό
    0.06
     controversy
    0.06
    Act Density 0.001%

    No Known Activations