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

    Neuronpedia

    INDEX
    Explanations

    bury

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cleanly
    -0.30
    API
    -0.28
    æ´ģåĩĢ
    -0.27
    /MIT
    -0.26
    /--
    -0.26
    æ¹ĸåĮº
    -0.26
    YN
    -0.25
    bootstrap
    -0.25
    èIJ¥åķĨ
    -0.25
    ç¥Ĺ
    -0.25
    POSITIVE LOGITS
    æī£
    0.29
    èħ¹
    0.26
    å¥ĸ
    0.25
     align
    0.24
    ient
    0.24
    奶
    0.24
     ölç
    0.23
    æķĻæ¡Ī
    0.23
     pNode
    0.23
    带æĿ¥æĽ´å¤ļ
    0.23
    Act Density 0.089%

    No Known Activations