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

    Neuronpedia

    INDEX
    Explanations

    XML parsing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hvor
    -0.06
    "All
    -0.06
    퓨
    -0.06
    年龄
    -0.06
    跑
    -0.06
     cabbage
    -0.06
    +)/
    -0.05
    {|
    -0.05
    رز
    -0.05
     heiß
    -0.05
    POSITIVE LOGITS
    Advanced
    0.07
    ाइट
    0.07
    09
    0.07
    orbit
    0.07
     Recursive
    0.07
    सल
    0.07
    manent
    0.06
     ре
    0.06
    .Token
    0.06
     Policies
    0.06
    Act Density 0.007%

    No Known Activations