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

    Neuronpedia

    INDEX
    Explanations

    secondary followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Aw
    1.15
    儿
    1.09
    ছিল
    1.04
    兒
    1.04
    ಫ್
    1.02
    𝙥
    1.02
     thisTrial
    1.01
    зе
    0.99
     রেজিম
    0.99
    দের
    0.99
    POSITIVE LOGITS
    ت
    1.12
    k
    1.10
    er
    1.05
    aries
    1.05
    ب
    1.02
    ing
    0.88
    ালন
    0.84
    ுங்கள்
    0.84
    র
    0.84
    hdr
    0.83
    Act Density 0.073%

    No Known Activations