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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pt
    -0.07
     census
    -0.07
    Iteration
    -0.07
     element
    -0.07
    ال
    -0.06
     GAME
    -0.06
     Winds
    -0.06
    Adv
    -0.06
     GB
    -0.06
     Wan
    -0.06
    POSITIVE LOGITS
     cuer
    0.07
    (";
    0.06
     /.
    0.06
    _FORCE
    0.06
     whopping
    0.06
     **/↵↵
    0.06
    SingleOrDefault
    0.06
     Depending
    0.06
    uppy
    0.06
     Willie
    0.06
    Act Density 0.028%

    No Known Activations