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

    Neuronpedia

    INDEX
    Explanations

    Mercedes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    naire
    -0.07
     Learning
    -0.07
    Professor
    -0.07
    Suite
    -0.07
    raise
    -0.06
    鐘
    -0.06
    ife
    -0.06
    ưởng
    -0.06
    "@
    -0.06
    问
    -0.06
    POSITIVE LOGITS
    ᐉ
    0.08
     dó
    0.07
    .Parcel
    0.07
     fals
    0.07
     collaps
    0.07
     device
    0.07
    시스
    0.07
    (strings
    0.07
     proble
    0.07
     bool
    0.07
    Act Density 0.004%

    No Known Activations