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

    Neuronpedia

    INDEX
    Explanations

    quantity of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    2.08
    ம்
    1.72
    تون
    1.52
     líqu
    1.48
    てください
    1.48
    ेल
    1.47
    いです
    1.44
    تری
    1.43
    openide
    1.42
     méridionale
    1.41
    POSITIVE LOGITS
    LE
    1.52
    𝔸
    1.52
    Α
    1.51
    ERT
    1.49
    ᴅ
    1.46
    罨
    1.46
    Ⅽ
    1.45
    RE
    1.44
    th
    1.40
    𝐼
    1.40
    Act Density 0.167%

    No Known Activations