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

    Neuronpedia

    INDEX
    Explanations

    map

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lihat
    -0.09
    选择
    -0.09
    ార్థ
    -0.08
     accessories
    -0.08
    查看
    -0.08
    ---------↵↵
    -0.08
     التفكير
    -0.08
    体现
    -0.08
    יניים
    -0.08
     επιλογ
    -0.08
    POSITIVE LOGITS
     Catalog
    0.10
     каталог
    0.10
     catalog
    0.10
     catalogs
    0.10
    Catalog
    0.09
     knowledge
    0.09
     renseign
    0.09
     확보
    0.09
     구축
    0.09
     erstellen
    0.09
    Act Density 0.019%

    No Known Activations