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

    Neuronpedia

    INDEX
    Explanations

    columns and rows

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (IP
    -0.07
     blackColor
    -0.06
    DLL
    -0.06
     선
    -0.06
     nightlife
    -0.06
    Levels
    -0.06
    Community
    -0.06
     Lif
    -0.06
     Sunny
    -0.06
     życ
    -0.06
    POSITIVE LOGITS
    ζα
    0.08
     ورزشی
    0.07
    宝
    0.06
     excited
    0.06
     совсем
    0.06
     обязательно
    0.06
     طلب
    0.06
    ováno
    0.06
     прибор
    0.06
    자를
    0.06
    Act Density 0.008%

    No Known Activations