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

    Neuronpedia

    INDEX
    Explanations

    workers' rights, hours, wages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Flowers
    -0.09
    .exc
    -0.08
    Obama
    -0.08
     Flowers
    -0.08
     flowers
    -0.08
     ears
    -0.08
     yay
    -0.08
    Chicken
    -0.08
     vino
    -0.08
     cilantro
    -0.07
    POSITIVE LOGITS
    待遇
    0.09
     Arbeits
    0.09
     Sicherheit
    0.08
     salar
    0.08
     unpaid
    0.08
     Länge
    0.08
    affen
    0.08
     fatigue
    0.08
     stature
    0.08
     Pflege
    0.07
    Act Density 0.010%

    No Known Activations