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

    Neuronpedia

    INDEX
    Explanations

    related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    тора
    -0.07
     дерева
    -0.07
    iant
    -0.06
     NAME
    -0.06
    director
    -0.06
    �
    -0.06
    gré
    -0.06
     DAO
    -0.06
    ался
    -0.06
    ponge
    -0.06
    POSITIVE LOGITS
    を作
    0.07
    searchModel
    0.06
    Ended
    0.06
    imson
    0.06
    ीख
    0.06
    ￥
    0.06
    ことは
    0.06
    Nuitka
    0.06
    }))↵↵
    0.06
    utowired
    0.06
    Act Density 0.002%

    No Known Activations