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

    Neuronpedia

    INDEX
    Explanations

    character

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     объект
    -0.07
     slam
    -0.07
     被
    -0.07
    スカ
    -0.07
    ọc
    -0.06
     Joy
    -0.06
     trval
    -0.06
     Kew
    -0.06
     Lonely
    -0.06
    :k
    -0.06
    POSITIVE LOGITS
    incorrect
    0.07
    [unit
    0.06
     arab
    0.06
     allure
    0.06
     barber
    0.06
    _COMPONENT
    0.06
    authors
    0.06
     assez
    0.06
    .getProduct
    0.06
        		↵
    0.06
    Act Density 0.024%

    No Known Activations