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

    Neuronpedia

    INDEX
    Explanations

    Unstructured data

    np_max-act · gemini-2.0-flash

    Tokens that occur in metadata or boilerplate parts of documents (timestamps, site/product info and similar routine/interface text).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    eprom
    -0.07
    folders
    -0.07
    ));
    -0.07
     お
    -0.06
    حدث
    -0.06
    ，说
    -0.06
     dalam
    -0.06
    ント
    -0.06
     thoroughly
    -0.06
     MPEG
    -0.06
    POSITIVE LOGITS
     ром
    0.07
    DOWN
    0.06
     partnerships
    0.06
    _ops
    0.06
    .Nil
    0.06
    ilmektedir
    0.06
     ジ
    0.06
     �
    0.06
    uyordu
    0.06
    ＿__
    0.06
    Act Density 0.760%

    No Known Activations