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

    Neuronpedia

    INDEX
    Explanations

    raising standards and spirits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ーク
    0.70
    ari
    0.66
    aik
    0.66
    ทาง
    0.65
     मजबूती
    0.65
    𝑵
    0.64
     ವ್ಯ
    0.64
    brug
    0.63
     వైర
    0.63
    强
    0.62
    POSITIVE LOGITS
     stakes
    1.17
     ante
    1.12
     spirits
    1.11
     standards
    1.06
     مستوى
    1.04
     Standards
    1.02
     Stakes
    0.99
     threshold
    0.98
     game
    0.95
     thresholds
    0.93
    Act Density 0.027%

    No Known Activations