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

    Neuronpedia

    INDEX
    Explanations

    Written text extracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bere
    -0.08
    ulings
    -0.07
     Kavanaugh
    -0.07
     شهرستان
    -0.07
     ambition
    -0.06
     des
    -0.06
    endl
    -0.06
    kách
    -0.06
    ادم
    -0.06
    \Post
    -0.06
    POSITIVE LOGITS
    ICENSE
    0.07
     Resorts
    0.07
    ollision
    0.07
     agreed
    0.07
    %/
    0.06
    expires
    0.06
    .quantity
    0.06
    .Millisecond
    0.06
     речов
    0.06
    ,System
    0.06
    Act Density 0.000%

    No Known Activations