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

    Neuronpedia

    INDEX
    Explanations

    specific types of events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ln
    0.43
     虽然
    0.41
     práci
    0.40
     жизнь
    0.39
    Excellent
    0.38
     excellent
    0.38
     çalışmalar
    0.37
    Mentor
    0.37
     tho
    0.37
     Đây
    0.37
    POSITIVE LOGITS
     특정
    0.47
    特定
    0.46
    に応じて
    0.44
     incentivize
    0.44
    イベント
    0.42
     potrebbe
    0.41
     സാമൂഹ
    0.41
    迎来
    0.40
     भाजप
    0.39
     event
    0.39
    Act Density 0.033%

    No Known Activations