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

    Neuronpedia

    INDEX
    Explanations

    reusable code and components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اس
    1.70
    স
    1.51
    с
    1.48
    서
    1.48
    shire
    1.47
    ᅱ
    1.43
    たら
    1.39
    서는
    1.38
    ography
    1.38
    ductory
    1.37
    POSITIVE LOGITS
    Ş
    1.38
    ל
    1.36
    ות
    1.34
    នុ
    1.28
    น
    1.28
     paramètres
    1.27
     וש
    1.23
    𝐁
    1.21
    analyse
    1.20
    lös
    1.19
    Act Density 0.005%

    No Known Activations