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

    Neuronpedia

    INDEX
    Explanations

    social security and benefits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pratiquer
    0.76
     défi
    0.73
     inductively
    0.72
     iterating
    0.72
    hashTree
    0.71
     목표
    0.71
     problém
    0.71
    infini
    0.70
    ostructures
    0.70
    केट
    0.69
    POSITIVE LOGITS
     benefits
    2.03
     Benefits
    1.77
    benefits
    1.70
     benefit
    1.69
    Benefits
    1.55
     pension
    1.46
     pensions
    1.43
     Benefit
    1.40
     BENEFITS
    1.40
    benefit
    1.38
    Act Density 0.056%

    No Known Activations