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

    Neuronpedia

    INDEX
    Explanations

    file paths and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    者が
    0.66
    لی
    0.61
    glise
    0.61
     кнопку
    0.60
     قیام
    0.59
    فی
    0.58
    ۵
    0.57
    ให้บริการ
    0.56
    刳
    0.56
    PolicyQuery
    0.55
    POSITIVE LOGITS
     File
    0.96
    文件
    0.88
     up
    0.85
     file
    0.85
     fopen
    0.77
    f
    0.76
     files
    0.73
     文件
    0.70
     AutoCAD
    0.70
     archivo
    0.69
    Act Density 0.830%

    No Known Activations