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

    Neuronpedia

    INDEX
    Explanations

    Explaining

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     peux
    -0.06
    敢
    -0.06
     уда
    -0.06
    必须
    -0.06
     корпус
    -0.06
     tỉ
    -0.06
     بغ
    -0.06
     σας
    -0.06
    .getMax
    -0.06
    eut
    -0.06
    POSITIVE LOGITS
     indian
    0.08
     Electricity
    0.07
     Indian
    0.07
     Occupational
    0.07
    ICLE
    0.06
    ational
    0.06
     Bicycle
    0.06
     صنعتی
    0.06
     corporate
    0.06
     curated
    0.06
    Act Density 0.050%

    No Known Activations