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

    Neuronpedia

    INDEX
    Explanations

    import os

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IOException
    0.41
    期刊
    0.40
     charge
    0.38
     target
    0.37
     NOI
    0.37
    ijken
    0.37
    ViewById
    0.36
    override
    0.36
    Report
    0.36
    ீர்கள்
    0.35
    POSITIVE LOGITS
     Picks
    0.42
     تحفظ
    0.42
    缭
    0.42
    랄
    0.40
    分かる
    0.38
    拯救
    0.38
    íg
    0.38
    ປະກອບ
    0.38
    ologa
    0.38
    🌶
    0.38
    Act Density 0.001%

    No Known Activations