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

    Neuronpedia

    INDEX
    Explanations

    updating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.53
    </h3>
    0.52
    0.50
     apresent
    0.47
    可以看出
    0.46
    increases
    0.45
     apresentam
    0.43
     aumento
    0.43
    </h2>
    0.43
    </b>
    0.43
    POSITIVE LOGITS
     更新
    0.71
    更新
    0.69
     обнов
    0.68
     обновление
    0.60
     updating
    0.59
     Updating
    0.59
    SecurityMarks
    0.58
     aggior
    0.58
     업데이트
    0.58
    update
    0.57
    Act Density 0.011%

    No Known Activations