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

    Neuronpedia

    INDEX
    Explanations

    revert

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ܕ
    -0.08
    밥
    -0.07
    bben
    -0.07
     bombing
    -0.07
    雷达
    -0.07
    ▥
    -0.07
    dać
    -0.07
    ▤
    -0.07
    かもしれません
    -0.07
     bada
    -0.07
    POSITIVE LOGITS
     reverted
    0.09
     revert
    0.08
     contributing
    0.08
    /book
    0.08
    游戏里的
    0.08
     RU
    0.08
     committing
    0.07
     exporter
    0.07
    -util
    0.07
     mixes
    0.07
    Act Density 0.006%

    No Known Activations