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

    Neuronpedia

    INDEX
    Explanations

    text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    报告
    -0.07
     Leonard
    -0.06
    那样
    -0.06
     голови
    -0.06
    .enable
    -0.06
    .matrix
    -0.05
     Sun
    -0.05
     mph
    -0.05
    用户
    -0.05
    .STATUS
    -0.05
    POSITIVE LOGITS
    дяки
    0.07
     cân
    0.07
    widgets
    0.07
    stagram
    0.06
    �
    0.06
    VED
    0.06
    едаг
    0.06
    .ExecuteScalar
    0.06
    VERSE
    0.06
    Filename
    0.06
    Act Density 0.312%

    No Known Activations