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

    Neuronpedia

    INDEX
    Explanations

    Number sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    监听页面
    -0.07
     chimney
    -0.07
    generator
    -0.07
     spindle
    -0.06
     LoginActivity
    -0.06
    testCase
    -0.06
     Km
    -0.06
     LX
    -0.06
    .assertEqual
    -0.06
     saya
    -0.06
    POSITIVE LOGITS
    ости
    0.07
    yas
    0.07
     titled
    0.06
    办公
    0.06
    [arr
    0.06
    (plot
    0.06
    不到
    0.06
     nomination
    0.06
    (tasks
    0.06
     khung
    0.06
    Act Density 0.048%

    No Known Activations