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

    Neuronpedia

    INDEX
    Explanations

    possessive actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     তীব্র
    0.39
    )}
    0.38
    <unused2148>
    0.38
     حصول
    0.37
     ഉത്തര
    0.37
    ));
    0.37
    ao
    0.37
     दरम्यान
    0.37
    jenigen
    0.37
     wodurch
    0.37
    POSITIVE LOGITS
     the
    0.55
     your
    0.48
     them
    0.47
     their
    0.46
     своей
    0.45
     свои
    0.45
    了自己的
    0.44
     his
    0.43
     swój
    0.43
    自己的
    0.42
    Act Density 0.114%

    No Known Activations