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

    Neuronpedia

    INDEX
    Explanations

    possessive forms of entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ünü
    0.53
    ğini
    0.45
    िकांनी
    0.42
     ਇੱਕ
    0.42
    他就
    0.41
    ുന്നു
    0.40
    他是
    0.40
     ہے۔
    0.40
     형태로
    0.39
     è
    0.39
    POSITIVE LOGITS
     యొక్క
    1.25
    ’
    1.20
    ရဲ့
    1.04
    님의
    1.02
    들의
    1.01
    '
    1.00
    idän
    0.99
    യുടെ
    0.98
    们的
    0.97
    ның
    0.94
    Act Density 0.103%

    No Known Activations