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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Buying
    -0.07
    unny
    -0.07
    (xi
    -0.07
     Existing
    -0.06
    _size
    -0.06
     predefined
    -0.06
    чу
    -0.06
    startDate
    -0.06
    ácil
    -0.06
    共
    -0.06
    POSITIVE LOGITS
     мер
    0.06
    ADB
    0.06
    .Err
    0.06
     Fr
    0.06
     kent
    0.06
     ї
    0.06
    --,
    0.06
    ['__
    0.06
     rocker
    0.06
    )↵↵
    0.06
    Act Density 0.061%

    No Known Activations