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

    Neuronpedia

    INDEX
    Explanations

    Turning directions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    highlight
    -0.07
     szczegółowo
    -0.07
    宣告
    -0.07
    Lon
    -0.07
     dần
    -0.07
    .Flag
    -0.07
     borç
    -0.07
    قطع
    -0.07
    奋力
    -0.07
    랖
    -0.07
    POSITIVE LOGITS
     Ma
    0.07
    )");
↵
    0.07
    -F
    0.07
    (step
    0.07
    希
    0.06
    缭
    0.06
     Spy
    0.06
     CSP
    0.06
     ス
    0.06
    "};↵
    0.06
    Act Density 0.007%

    No Known Activations