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

    Neuronpedia

    INDEX
    Explanations

    text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _positions
    -0.06
    pdo
    -0.06
    -independent
    -0.06
     beş
    -0.06
    itar
    -0.06
     Models
    -0.06
    Headers
    -0.06
    roud
    -0.06
     unusual
    -0.06
     jury
    -0.06
    POSITIVE LOGITS
    xmin
    0.07
     Discuss
    0.07
    *******/↵
    0.06
     dedication
    0.06
    グ
    0.06
     kimse
    0.06
    Discuss
    0.06
    /ch
    0.06
    ải
    0.06
     IData
    0.06
    Act Density 0.003%

    No Known Activations