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

    Neuronpedia

    INDEX
    Explanations

    tested

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pepper
    -0.06
    เมตร
    -0.06
     lineno
    -0.06
    ukarı
    -0.06
     UIImage
    -0.06
     शब
    -0.06
     ngữ
    -0.06
     scale
    -0.06
    creator
    -0.06
    _method
    -0.06
    POSITIVE LOGITS
    (mut
    0.08
     щоб
    0.06
     Acad
    0.06
    ниць
    0.06
    シー
    0.06
     automáticamente
    0.06
     může
    0.06
    іль
    0.06
    -off
    0.06
     afterwards
    0.06
    Act Density 0.012%

    No Known Activations