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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    筼
    -0.07
    תש
    -0.07
    净化
    -0.07
    ご覧
    -0.06
    arith
    -0.06
     pump
    -0.06
    っぱ
    -0.06
     Boeh
    -0.06
     Miy
    -0.06
    т
    -0.06
    POSITIVE LOGITS
     breadcrumb
    0.07
    成功的
    0.07
    ㆀ
    0.06
     bordel
    0.06
    Average
    0.06
     hilar
    0.06
    .isFile
    0.06
     cuando
    0.06
     pakistan
    0.06
     hired
    0.06
    Act Density 0.002%

    No Known Activations