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

    Neuronpedia

    INDEX
    Explanations

    Document/article metadata

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    emb
    -0.07
     finder
    -0.07
    -li
    -0.07
    asin
    -0.07
     //{↵
    -0.07
    ingleton
    -0.06
     entering
    -0.06
    ,max
    -0.06
     nie
    -0.06
    .of
    -0.06
    POSITIVE LOGITS
    Uvs
    0.07
     мам
    0.07
     рассказ
    0.06
     Momentum
    0.06
     Tropical
    0.06
     verdienen
    0.06
     nhấn
    0.06
    θηκε
    0.06
    继续
    0.06
    자동
    0.06
    Act Density 0.032%

    No Known Activations