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

    Neuronpedia

    INDEX
    Explanations

    loung

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    locals
    -0.08
    .Output
    -0.07
    .bytes
    -0.07
     navbar
    -0.07
    مت
    -0.07
    .views
    -0.07
     intéress
    -0.07
     thu
    -0.07
    /*----------------------------------------------------------------
    -0.07
    _cn
    -0.07
    POSITIVE LOGITS
    +↵
    0.08
    읔
    0.07
    遗迹
    0.07
     glory
    0.07
    演习
    0.07
    低い
    0.07
     ранее
    0.07
    -air
    0.07
    eshire
    0.07
     وإذا
    0.07
    Act Density 0.056%

    No Known Activations