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

    Neuronpedia

    INDEX
    Explanations

    _test

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OL
    -0.07
     abb
    -0.07
    ıkl
    -0.07
    ol
    -0.06
     mM
    -0.06
    gaard
    -0.06
     MIL
    -0.06
    uluğ
    -0.06
     logo
    -0.06
    keeper
    -0.06
    POSITIVE LOGITS
    搬
    0.08
    025
    0.06
    輪
    0.06
     très
    0.06
     subsets
    0.06
    TouchUpInside
    0.06
    Needed
    0.06
    Trou
    0.06
    рач
    0.06
     indis
    0.06
    Act Density 0.003%

    No Known Activations