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

    Neuronpedia

    INDEX
    Explanations

    analyze and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝖆
    0.80
    waitForIdleSync
    0.77
    涹
    0.77
    訝
    0.74
    欷
    0.74
    菈
    0.73
    𒌅
    0.73
    ᙱ
    0.73
    ясплат
    0.72
    㛲
    0.72
    POSITIVE LOGITS
    分析
    0.88
    ,
    0.71
    ①
    0.67
     analyze
    0.66
    0.66
    ↵
    0.66
     analyse
    0.66
    ，
    0.64
     分析
    0.64
     [
    0.62
    Act Density 0.002%

    No Known Activations