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

    Neuronpedia

    INDEX
    Explanations

    SQL and category names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $，
    0.27
    ICPSR
    0.26
    .??
    0.26
    上下文
    0.26
    classAttribute
    0.26
     可以
    0.25
     输出
    0.25
    ម្លៃ
    0.25
    ulloch
    0.25
    '_
    0.25
    POSITIVE LOGITS
     Departments
    0.33
     Type
    0.31
     Techniques
    0.31
     Department
    0.31
     Programming
    0.31
     Category
    0.30
     Consultant
    0.29
     Section
    0.29
     Methodology
    0.29
     Jenis
    0.29
    Act Density 0.021%

    No Known Activations