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

    Neuronpedia

    INDEX
    Explanations

    includes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    `,↵
    -0.06
    σκευή
    -0.06
     جه
    -0.06
     Pon
    -0.06
    .",↵
    -0.06
    45
    -0.06
     Wireless
    -0.06
    ۳۵
    -0.06
    易
    -0.06
    يري
    -0.06
    POSITIVE LOGITS
     المت
    0.07
    แน
    0.07
     gums
    0.07
     обычно
    0.07
     suoi
    0.06
    vestment
    0.06
     yc
    0.06
    ONGLONG
    0.06
     setBackgroundImage
    0.06
     unp
    0.06
    Act Density 0.003%

    No Known Activations