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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     analsex
    -0.07
     развити
    -0.07
     ledna
    -0.07
    ožná
    -0.07
     ổn
    -0.06
    aniu
    -0.06
     INTO
    -0.06
     وسلم
    -0.06
     testData
    -0.06
     yönetim
    -0.06
    POSITIVE LOGITS
     insensitive
    0.06
     berry
    0.06
    หล
    0.06
    Course
    0.06
    طار
    0.06
     topical
    0.06
     Examiner
    0.06
    Sarah
    0.06
    Ace
    0.06
     mush
    0.06
    Act Density 0.000%

    No Known Activations