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

    Neuronpedia

    INDEX
    Explanations

    regex call

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     камера
    0.52
    ляр
    0.45
    氙
    0.45
     રહી
    0.45
    뢨
    0.44
     વડે
    0.44
     комп
    0.44
     физи
    0.43
     nhé
    0.43
     रिप्रोडक्शन
    0.43
    POSITIVE LOGITS
     and
    0.52
    প্রায়
    0.50
    erk
    0.47
    for
    0.45
    ed
    0.45
     as
    0.44
     ancient
    0.43
     erine
    0.43
     more
    0.43
    প্রায়
    0.43
    Act Density 0.001%

    No Known Activations