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

    Neuronpedia

    INDEX
    Explanations

    pronouns and functional words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     проє
    1.50
     проєкту
    1.49
     ✨
    1.39
     reimag
    1.34
    📍
    1.31
     TikTok
    1.23
    ✨
    1.22
     livestream
    1.22
     🔥
    1.20
     👇
    1.18
    POSITIVE LOGITS
    非常的
    1.54
     computerized
    1.49
     سوف
    1.45
     you
    1.43
    很多的
    1.43
     alot
    1.40
     보면은
    1.39
    ｙ
    1.39
     equipments
    1.38
     mempunyai
    1.37
    Act Density 0.004%

    No Known Activations