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

    Neuronpedia

    INDEX
    Explanations

    publishers new latest editions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Wait
    0.43
    ActiveClass
    0.39
    Origins
    0.39
     documenti
    0.38
    पीरिय
    0.37
    Radians
    0.37
    狈
    0.37
    hoy
    0.36
     آنلاین
    0.36
    нда
    0.36
    POSITIVE LOGITS
     Sales
    0.50
     Latest
    0.50
     Delhi
    0.48
     Publisher
    0.48
     publishers
    0.47
     Publishers
    0.47
     sales
    0.46
     neuest
    0.45
     প্রকাশক
    0.45
     लेटेस्ट
    0.45
    Act Density 0.003%

    No Known Activations