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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elephant
    -0.07
    美术馆
    -0.07
     Bel
    -0.07
    攘
    -0.07
    acute
    -0.07
    itecture
    -0.07
     Gel
    -0.07
    戾
    -0.07
    Mas
    -0.07
     Adv
    -0.07
    POSITIVE LOGITS
     eso
    0.06
    .And
    0.06
     vọng
    0.06
    (IS
    0.06
    leccion
    0.06
     enough
    0.06
    主管部门
    0.06
    市场监管
    0.06
    看看
    0.06
     paar
    0.06
    Act Density 0.001%

    No Known Activations