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

    Neuronpedia

    INDEX
    Explanations

    problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    通過
    -0.06
     Rosen
    -0.06
    /gtest
    -0.06
    몬
    -0.06
     userType
    -0.06
    需
    -0.06
    findBy
    -0.06
     tiến
    -0.06
    чил
    -0.06
     ของ
    -0.06
    POSITIVE LOGITS
    racak
    0.08
    _canvas
    0.07
    ernen
    0.07
     taşıy
    0.06
    akat
    0.06
    +]
    0.06
    fffffff
    0.06
     defeats
    0.06
    ans
    0.06
     uneasy
    0.06
    Act Density 0.050%

    No Known Activations