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

    Neuronpedia

    INDEX
    Explanations

    curves / bending

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    loan
    -0.08
    ◤
    -0.08
     aft
    -0.07
     infections
    -0.07
    🍮
    -0.07
    (pDX
    -0.07
    年产值
    -0.07
    钊
    -0.07
    CppCodeGenWriteBarrier
    -0.07
     fences
    -0.07
    POSITIVE LOGITS
    .search
    0.07
    ]));
    0.07
    西方
    0.07
    玩家们
    0.07
    .bot
    0.07
    WSC
    0.06
    万物
    0.06
    .PageSize
    0.06
     CreateUser
    0.06
    Part
    0.06
    Act Density 0.034%

    No Known Activations