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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hotels
    -0.07
    icket
    -0.07
     Entrepreneur
    -0.07
    Bitcoin
    -0.07
    .utils
    -0.07
    ритор
    -0.06
    .stats
    -0.06
     Buffett
    -0.06
    customers
    -0.06
    müş
    -0.06
    POSITIVE LOGITS
    eki
    0.09
     limits
    0.07
     bronze
    0.07
    达不到
    0.07
    mph
    0.07
     집
    0.07
    finance
    0.07
    具体情况
    0.07
    дает
    0.07
     assembling
    0.07
    Act Density 0.006%

    No Known Activations