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

    Neuronpedia

    INDEX
    Explanations

    Latin translation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Netflix
    -0.11
    Netflix
    -0.10
     Oprah
    -0.09
     netflix
    -0.09
     concierge
    -0.09
    腾讯
    -0.09
    奋斗
    -0.09
     sunglasses
    -0.09
    深圳
    -0.09
     ESPN
    -0.09
    POSITIVE LOGITS
     ancient
    0.12
     medieval
    0.12
     Medieval
    0.11
     древ
    0.11
     Ancient
    0.11
    �
    0.10
     fossils
    0.09
    古
    0.09
     genus
    0.09
     Gothic
    0.09
    Act Density 0.018%

    No Known Activations