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

    Neuronpedia

    INDEX
    Explanations

    mathematical geometry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ế
    -0.08
     Reid
    -0.07
    _OPEN
    -0.07
    辗转
    -0.07
    نغ
    -0.07
     бюджет
    -0.07
    _Right
    -0.06
    واب
    -0.06
    它们
    -0.06
    哪些
    -0.06
    POSITIVE LOGITS
    .Factory
    0.07
    หมวด
    0.07
    套餐
    0.07
    _TABLE
    0.07
    Class
    0.07
    �
    0.07
     מילי
    0.06
    땔
    0.06
    琉璃
    0.06
    ثلاث
    0.06
    Act Density 0.007%

    No Known Activations