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

    Neuronpedia

    INDEX
    Explanations

    Describing a problem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aires
    -0.07
    azo
    -0.07
    ’яз
    -0.06
     Richmond
    -0.06
    pagesize
    -0.06
    िद
    -0.06
     prized
    -0.06
    .addValue
    -0.06
    ох
    -0.06
    ElapsedTime
    -0.06
    POSITIVE LOGITS
     центр
    0.07
    richt
    0.07
     догов
    0.07
    008
    0.07
    Senator
    0.07
    ultimate
    0.06
     Senator
    0.06
    .Is
    0.06
     polls
    0.06
    ره
    0.06
    Act Density 0.100%

    No Known Activations