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

    Neuronpedia

    INDEX
    Explanations

    Which followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    綃
    1.33
    ות
    1.28
    いっぱい
    1.23
     whatnot
    1.19
    ларга
    1.13
    fellow
    1.12
    ותו
    1.12
    ים
    1.09
    おります
    1.09
    ності
    1.09
    POSITIVE LOGITS
    吒
    1.46
    يد
    1.29
     কিনা
    1.22
     sebenarnya
    1.19
    되었다
    1.18
     setores
    1.17
     nessuna
    1.17
    koľ
    1.16
     министер
    1.16
    はお
    1.15
    Act Density 0.032%

    No Known Activations