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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash

    The neuron activates on bracketed reference or citation markers (e.g. “[1]”, “[2]”) used to point to footnotes or external links.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    본
    -0.06
    shots
    -0.06
    .skill
    -0.06
    _ON
    -0.06
    [url
    -0.06
    _two
    -0.06
    ارب
    -0.06
    문
    -0.06
    ophil
    -0.06
    暮
    -0.06
    POSITIVE LOGITS
    redirectTo
    0.07
     rost
    0.07
     edited
    0.07
     distributes
    0.06
     грав
    0.06
     floors
    0.06
     }}
    0.06
     respir
    0.06
     更新
    0.06
     )}↵
    0.06
    Act Density 0.008%

    No Known Activations