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

    Neuronpedia

    INDEX
    Explanations

    wage gap

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     leveraging
    0.65
     Leveraging
    0.65
     reimag
    0.62
     egregious
    0.60
     impactful
    0.57
    Thankfully
    0.57
     unglaublich
    0.55
     нужно
    0.54
     Thankfully
    0.54
    ंसाठी
    0.53
    POSITIVE LOGITS
     constitutes
    0.77
     constitute
    0.76
     belonging
    0.72
     fulfils
    0.71
     hardly
    0.71
     belongs
    0.70
     hitherto
    0.67
     envis
    0.66
     envisaged
    0.66
     constituting
    0.66
    Act Density 0.004%

    No Known Activations