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

    Neuronpedia

    INDEX
    Explanations

    start

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tyto
    -0.07
    Studio
    -0.07
     Nested
    -0.07
    віль
    -0.07
     kurs
    -0.06
    etzt
    -0.06
    ňuje
    -0.06
    奧
    -0.06
     zdroj
    -0.06
     onView
    -0.06
    POSITIVE LOGITS
    约
    0.07
    因为
    0.06
    ‌ها
    0.06
    spr
    0.06
     festivities
    0.06
     wonder
    0.06
     avg
    0.06
     Offset
    0.06
    \s
    0.06
     �
    0.05
    Act Density 0.019%

    No Known Activations