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

    Neuronpedia

    INDEX
    Explanations

    buried

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Citadel
    -0.07
    江北
    -0.07
    ㇼ
    -0.06
     subclass
    -0.06
    莪
    -0.06
    氿
    -0.06
    跬
    -0.06
    餐廳
    -0.06
    澴
    -0.06
     AIR
    -0.06
    POSITIVE LOGITS
     greatly
    0.07
     lễ
    0.07
    อาการ
    0.07
     buried
    0.07
    造福
    0.07
     favour
    0.07
     Names
    0.07
     influences
    0.07
     careers
    0.07
    propertyName
    0.07
    Act Density 0.002%

    No Known Activations