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

    Neuronpedia

    INDEX
    Explanations

    xml version="1.0"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     entender
    1.05
     hiểu
    0.96
     Thiết
    0.93
    Style
    0.92
     thiết
    0.92
    vdots
    0.91
    Đi
    0.88
     comboBox
    0.88
    ่อง
    0.87
    Path
    0.87
    POSITIVE LOGITS
    ="-
    0.89
    ="
    0.84
     control
    0.84
    =”
    0.80
    ＝
    0.79
    ுக்கு
    0.78
     tram
    0.77
    na
    0.74
     aggravation
    0.72
     लिये
    0.72
    Act Density 0.001%

    No Known Activations