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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ユーザー
    -0.08
    .populate
    -0.07
     prosecuting
    -0.07
     utilizando
    -0.07
    葡萄牙
    -0.07
     proton
    -0.06
     lim
    -0.06
     equiv
    -0.06
     downloadable
    -0.06
    تنا
    -0.06
    POSITIVE LOGITS
    .by
    0.07
    ˧
    0.07
    _STR
    0.07
    Tech
    0.07
    馊
    0.07
     smarter
    0.07
     오�
    0.06
    Description
    0.06
    _misc
    0.06
    召回
    0.06
    Act Density 0.043%

    No Known Activations