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

    Neuronpedia

    INDEX
    Explanations

    animations, especially UI animations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    varez
    -0.73
    新增
    -0.68
    两
    -0.66
    grained
    -0.66
     Ferreira
    -0.66
    tese
    -0.65
    ffion
    -0.65
    omiast
    -0.65
    electron
    -0.64
    堃
    -0.64
    POSITIVE LOGITS
     sentry
    0.67
    Dedu
    0.67
    Suggest
    0.67
    ッテ
    0.66
     suges
    0.65
    ストーリー
    0.65
     Lair
    0.65
    getLong
    0.64
    鯵
    0.63
    animated
    0.63
    Act Density 0.077%

    No Known Activations