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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -INFRINGEMENT
    -0.06
     ids
    -0.06
    す
    -0.06
    介
    -0.06
    _PAR
    -0.06
     Newcastle
    -0.06
     Collision
    -0.06
    іблі
    -0.06
    ключ
    -0.06
     Wrapper
    -0.06
    POSITIVE LOGITS
     healthy
    0.07
     Muse
    0.07
     bağlantılar
    0.06
     appart
    0.06
     โดย
    0.06
    petto
    0.06
    Dans
    0.06
    ницт
    0.06
    (Channel
    0.06
    ється
    0.06
    Act Density 0.055%

    No Known Activations