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

    Neuronpedia

    INDEX
    Explanations

    fairness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     punctured
    0.41
    kových
    0.41
     McCulloch
    0.41
     tarefas
    0.40
     பி
    0.40
     dulce
    0.39
     HMS
    0.39
     Lúc
    0.38
    uario
    0.38
     कच्छ
    0.38
    POSITIVE LOGITS
    fair
    0.96
    Fair
    0.94
     fair
    0.91
    公平
    0.89
     Fair
    0.88
     fairness
    0.88
     unfair
    0.87
    unfair
    0.85
     справед
    0.81
     fairer
    0.80
    Act Density 0.008%

    No Known Activations