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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash

    This neuron fires on tokens that appear as part of section headers or document metadata labels (e.g., headings like “Monetization Strategies,” “Other Delivery Information,” “Immunohistochemical markers,” or “Content ideas”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Different
    -0.07
     First
    -0.07
    Trong
    -0.07
    different
    -0.06
    Si
    -0.06
    #:
    -0.06
     first
    -0.06
    Round
    -0.06
    elementType
    -0.06
     ATTR
    -0.06
    POSITIVE LOGITS
     Sanct
    0.08
     */,
    0.06
    gements
    0.06
    >';↵
    0.06
    640
    0.06
    _try
    0.06
    .jackson
    0.06
    eed
    0.06
    官方
    0.06
    gems
    0.06
    Act Density 0.197%

    No Known Activations