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

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives for materials or capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ナナ
    0.46
    比特
    0.42
     tarmac
    0.42
    헐
    0.41
     मुठभे
    0.40
    Pixel
    0.40
    Generic
    0.40
    Jake
    0.40
    เข้า
    0.39
     समीर
    0.39
    POSITIVE LOGITS
     Comments
    0.48
    umos
    0.48
     Employees
    0.47
     Arrange
    0.47
     spada
    0.46
     Managers
    0.46
     Announcements
    0.45
     Afternoon
    0.45
     Appropriate
    0.44
     Yearbook
    0.44
    Act Density 0.008%

    No Known Activations