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

    Neuronpedia

    INDEX
    Explanations

    nanop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    骨æŀ¶
    -0.30
    åĽĽèĤ¢
    -0.30
    ære
    -0.28
    åİŁåŀĭ
    -0.27
     Brigham
    -0.26
    æĺ¯ä¸Ģ款
    -0.26
     Affero
    -0.26
    __,__
    -0.25
    ä½ľä¸ºä¸Ģç§į
    -0.25
    åĪĸ
    -0.24
    POSITIVE LOGITS
    adian
    0.28
    upt
    0.28
     Ou
    0.27
    uro
    0.27
    irma
    0.27
     ster
    0.26
    icultural
    0.26
    話
    0.25
    inja
    0.25
    nest
    0.25
    Act Density 0.082%

    No Known Activations