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

    Neuronpedia

    INDEX
    Explanations

    error handling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rush
    -0.08
    undet
    -0.08
    Kenn
    -0.08
     площади
    -0.08
     offices
    -0.08
     percentages
    -0.07
    elaars
    -0.07
     spac
    -0.07
     Fläche
    -0.07
     площадь
    -0.07
    POSITIVE LOGITS
    "errors
    0.08
    0.08
     resetting
    0.08
     ficha
    0.08
     কারণ
    0.08
     왜
    0.08
     техничес
    0.07
     അമ
    0.07
    тийн
    0.07
     കാരണം
    0.07
    Act Density 0.000%

    No Known Activations