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

    Neuronpedia

    INDEX
    Explanations

    specific

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ASC
    -0.08
     hac
    -0.07
     دمشق
    -0.07
    .getLength
    -0.07
    顼
    -0.07
    ousy
    -0.07
     móc
    -0.07
    irut
    -0.07
    ╒
    -0.07
    تمع
    -0.07
    POSITIVE LOGITS
    펜
    0.07
     """
    0.06
     Kelly
    0.06
    |M
    0.06
    显示出
    0.06
    秒
    0.06
     имеют
    0.06
    演讲
    0.06
    lets
    0.06
    䏝
    0.06
    Act Density 0.003%

    No Known Activations