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

    Neuronpedia

    INDEX
    Explanations

    matplotlib pyplot plots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lay
    0.55
    8
    0.54
    9
    0.52
    ds
    0.51
    h
    0.51
    g
    0.49
    ast
    0.49
    row
    0.49
    desc
    0.49
    link
    0.48
    POSITIVE LOGITS
    క్షణ
    0.51
    ్వర
    0.50
    语句
    0.49
    كيد
    0.47
     开始
    0.47
    <unused648>
    0.47
    喑
    0.46
     график
    0.46
     strListName
    0.46
     종료
    0.46
    Act Density 0.028%

    No Known Activations