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

    Neuronpedia

    INDEX
    Explanations

    with open(

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    すべての
    0.46
    コピー
    0.46
    uito
    0.42
    कार्य
    0.41
    copy
    0.40
    have
    0.40
    ant
    0.39
    ore
    0.39
    ource
    0.39
    Folder
    0.38
    POSITIVE LOGITS
    指定的
    0.43
     `./
    0.42
     `${
    0.41
     kraj
    0.41
     mond
    0.39
     './
    0.39
     Georgetown
    0.39
    тым
    0.38
     svojim
    0.37
    陴
    0.37
    Act Density 0.044%

    No Known Activations