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

    Neuronpedia

    INDEX
    Explanations

    guide, benefit, avoids damage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grafico
    0.56
     grafik
    0.55
    グラフ
    0.52
    图形
    0.52
     graphs
    0.51
     графи
    0.50
     〢
    0.50
     그래프
    0.50
     graphing
    0.50
    下图
    0.50
    POSITIVE LOGITS
    Incremental
    0.40
     phased
    0.38
    λικά
    0.38
     incremental
    0.37
    eru
    0.37
    íram
    0.37
    ario
    0.36
    comer
    0.36
    秇
    0.36
     how
    0.36
    Act Density 0.000%

    No Known Activations