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

    Neuronpedia

    INDEX
    Explanations

    Latest work from OpenAI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Buzz
    0.43
     खिला
    0.42
    作为
    0.41
    Alcohol
    0.41
    -
    0.41
    碧
    0.41
    гла
    0.40
    Type
    0.40
    Country
    0.40
    欢迎
    0.40
    POSITIVE LOGITS
    dzie
    0.52
     중국
    0.50
    وامی
    0.48
     그래프
    0.48
     oksid
    0.47
    𝘳
    0.47
    𝘨
    0.47
    𝘴
    0.47
     mês
    0.45
     serat
    0.45
    Act Density 0.004%

    No Known Activations