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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ur
    -0.06
     Foo
    -0.06
    _vue
    -0.06
     mushroom
    -0.06
    imize
    -0.06
     Img
    -0.06
     }];↵↵
    -0.06
    (coeff
    -0.06
    ekyll
    -0.06
     sehr
    -0.05
    POSITIVE LOGITS
    谵
    0.07
    江山
    0.07
    加深
    0.07
    гад
    0.07
    /player
    0.07
    tant
    0.07
    人が
    0.07
     Çünkü
    0.07
     כאמור
    0.07
     CAST
    0.06
    Act Density 0.028%

    No Known Activations