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

    Neuronpedia

    INDEX
    Explanations

    math and golang code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    賜
    0.44
    ỉ
    0.38
    咸
    0.38
    烦
    0.37
    创建
    0.37
     ціка
    0.36
     ফকির
    0.36
     Tammy
    0.35
    空间
    0.35
     Там
    0.35
    POSITIVE LOGITS
     footwear
    0.40
    Ref
    0.40
    Media
    0.39
    Lists
    0.38
    Metal
    0.38
    Refrigerator
    0.38
     detergent
    0.37
     detoxification
    0.37
    Af
    0.36
    Mobile
    0.36
    Act Density 0.001%

    No Known Activations