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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    press
    -0.28
    å¦ĤæĦı
    -0.27
     Counsel
    -0.26
    æĺİçŁ¥
    -0.25
     sens
    -0.25
     ters
    -0.25
    åIJĮçŃī
    -0.25
     Meaning
    -0.25
    ons
    -0.24
    own
    -0.24
    POSITIVE LOGITS
    åıĸæļĸ
    0.30
    getParam
    0.28
    igar
    0.28
    æĥħåĨµè¿Ľè¡Į
    0.26
    specs
    0.26
     dinners
    0.25
    |%
    0.25
     legends
    0.25
    ');↵↵↵↵
    0.25
    æĹĨ
    0.24
    Act Density 0.005%

    No Known Activations