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

    Neuronpedia

    INDEX
    Explanations

    fair wages, compensation, or admissions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    忘记
    0.46
     evoking
    0.45
    晓
    0.45
     ignore
    0.45
     corrobor
    0.43
     компании
    0.43
    忽略
    0.43
     общества
    0.43
    boxylate
    0.43
     imaginations
    0.42
    POSITIVE LOGITS
     fairness
    0.69
     Fairness
    0.57
     fairer
    0.55
    fair
    0.50
    Fair
    0.47
     fair
    0.44
     tax
    0.44
     unfair
    0.43
     tema
    0.42
    tema
    0.42
    Act Density 0.010%

    No Known Activations