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

    Neuronpedia

    INDEX
    Explanations

    Common English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    し
    -0.08
    xs
    -0.07
     cakes
    -0.07
     grav
    -0.07
    057
    -0.07
    080
    -0.06
    =");↵
    -0.06
     yapıldı
    -0.06
    ayet
    -0.06
    fx
    -0.06
    POSITIVE LOGITS
    ("(%
    0.07
     东
    0.06
     л
    0.06
    енню
    0.06
     λο
    0.06
    стит
    0.06
    Updating
    0.06
    _PERIOD
    0.06
    ��
    0.06
    افی
    0.06
    Act Density 0.272%

    No Known Activations