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

    Neuronpedia

    INDEX
    Explanations

    examples, format, result, chart, graph

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    適
    0.51
     Suitable
    0.50
    适当
    0.46
    适合
    0.45
     suitable
    0.44
    Suitable
    0.44
     適
    0.43
     unsuitable
    0.43
     Appropriate
    0.42
    헤
    0.42
    POSITIVE LOGITS
    图
    0.69
    所示
    0.66
    示
    0.64
    圖
    0.64
    図
    0.57
     shown
    0.56
     graph
    0.55
    图中
    0.55
    graph
    0.54
     chart
    0.54
    Act Density 0.005%

    No Known Activations