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

    Neuronpedia

    INDEX
    Explanations

    round

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wobec
    -0.89
    zu
    -0.75
     Bür
    -0.71
    డు
    -0.70
     CPO
    -0.68
    Reds
    -0.68
    atelyn
    -0.67
     Endlich
    -0.67
    marca
    -0.67
    lines
    -0.67
    POSITIVE LOGITS
     round
    3.88
    round
    3.16
    Round
    3.09
     Round
    2.81
     ROUND
    2.53
    ROUND
    2.38
     круг
    1.80
    往
    1.80
     Roundtable
    1.75
     rounded
    1.70
    Act Density 0.027%

    No Known Activations