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

    Neuronpedia

    INDEX
    Explanations

    dimension shape

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    工程师
    -0.08
    ยอด
    -0.07
    镧
    -0.07
    ｔ
    -0.06
     لدي
    -0.06
    昆虫
    -0.06
    магазин
    -0.06
    茭
    -0.06
    起草
    -0.06
    Davis
    -0.06
    POSITIVE LOGITS
    Models
    0.07
     Usually
    0.07
    counts
    0.07
     Allow
    0.07
    贴吧
    0.07
    shape
    0.07
     Sat
    0.07
     lockdown
    0.06
    และ
    0.06
    .Or
    0.06
    Act Density 0.001%

    No Known Activations