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

    Neuronpedia

    INDEX
    Explanations

    geography

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    گان
    -0.06
    .wall
    -0.06
     ngành
    -0.06
     Else
    -0.06
    .blog
    -0.06
    724
    -0.06
    ELS
    -0.05
    Tk
    -0.05
    ẽ
    -0.05
     Bearings
    -0.05
    POSITIVE LOGITS
     Kı
    0.08
    (arc
    0.07
    ifying
    0.07
    !")↵↵
    0.07
    ..↵↵
    0.07
     defines
    0.07
     *);↵
    0.07
    Commerce
    0.06
     dagen
    0.06
    ARGET
    0.06
    Act Density 0.011%

    No Known Activations