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

    Neuronpedia

    INDEX
    Explanations

    lucky

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    approx
    -0.29
    å¤ļç§įå½¢å¼ı
    -0.27
    lications
    -0.27
    citation
    -0.25
    metis
    -0.24
    æĿ¡
    -0.24
    cons
    -0.24
    asis
    -0.24
    æ¢Ŀ
    -0.23
    /pi
    -0.23
    POSITIVE LOGITS
    è¿ĽæĿ¥
    0.26
    ington
    0.25
    çĽĸ
    0.25
    eut
    0.25
    è§ģ解
    0.24
    peer
    0.24
    shan
    0.24
     contemporary
    0.24
    elite
    0.24
    è¿ĻéĩĮæľī
    0.24
    Act Density 1.669%

    No Known Activations