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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     participação
    -0.07
    𝚔
    -0.07
    archivo
    -0.07
    윤
    -0.06
     ơn
    -0.06
    day
    -0.06
     Św
    -0.06
    哞
    -0.06
    miş
    -0.06
     אנו
    -0.06
    POSITIVE LOGITS
     layers
    0.07
     э
    0.07
    包围
    0.07
     features
    0.07
    equiv
    0.07
    持久
    0.07
    橄榄
    0.07
    ota
    0.07
     Features
    0.07
    东西
    0.07
    Act Density 0.041%

    No Known Activations