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

    Neuronpedia

    INDEX
    Explanations

    improvements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    диви
    -0.07
     docking
    -0.07
     další
    -0.06
     position
    -0.06
    ｝
    -0.06
    pl
    -0.06
     winding
    -0.06
     Dice
    -0.06
     snatch
    -0.06
     fizz
    -0.06
    POSITIVE LOGITS
     improvements
    0.33
     improvement
    0.14
    vements
    0.12
     Improvement
    0.11
     enhancements
    0.09
    ancements
    0.07
    uards
    0.07
    ishments
    0.07
     successes
    0.07
     OA
    0.07
    Act Density 0.007%

    No Known Activations