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

    Neuronpedia

    INDEX
    Explanations

    ato

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     불구하고
    1.45
    mdash
    1.43
    й
    1.21
    ️⃣
    1.20
    тация
    1.15
    ต์
    1.14
    امة
    1.12
    𝗨
    1.11
    dplyr
    1.10
    ərbay
    1.09
    POSITIVE LOGITS
    الم
    1.37
    क
    1.34
    وكان
    1.33
    வ
    1.28
    一个
    1.26
    hrs
    1.24
    vij
    1.22
     要
    1.20
    ש
    1.19
    感觉
    1.18
    Act Density 0.002%

    No Known Activations