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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '../
    -0.08
    눉
    -0.07
    Austin
    -0.07
    感到
    -0.07
     ful
    -0.07
    ON
    -0.07
     Assuming
    -0.07
    ())
↵
    -0.07
     characteristics
    -0.07
    tracts
    -0.07
    POSITIVE LOGITS
    汨
    0.07
    퓲
    0.07
    Tabs
    0.07
    ילת
    0.07
    crire
    0.07
     ky
    0.07
    عدد
    0.07
     bols
    0.07
    aya
    0.07
    悔
    0.07
    Act Density 0.001%

    No Known Activations