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

    Neuronpedia

    INDEX
    Explanations

    copyright and privacy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    个人信æģ¯
    -0.35
    éļIJç§ģ
    -0.35
    ialized
    -0.33
    Privacy
    -0.31
     privacy
    -0.31
     Confidential
    -0.30
     Datensch
    -0.30
     ê°ľìĿ¸ìłķë³´
    -0.30
     Privacy
    -0.28
     GDPR
    -0.27
    POSITIVE LOGITS
    åĨł
    0.28
    ëĭ¨
    0.28
    éĢŀ
    0.26
    æĺ¯éĿŀ
    0.26
    椽
    0.26
    akt
    0.25
     dispens
    0.25
    鼷
    0.25
    andin
    0.25
    æĹĹ
    0.25
    Act Density 0.472%

    No Known Activations