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

    Neuronpedia

    INDEX
    Explanations

    errors and variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    有用
    0.42
    危機
    0.41
    cipit
    0.39
     лого
    0.38
     زور
    0.38
     राजप
    0.38
     работо
    0.38
     firepower
    0.38
     खतरे
    0.38
     клю
    0.38
    POSITIVE LOGITS
     imperfections
    1.23
     inhomogeneities
    1.16
     imperfect
    1.09
     inaccuracies
    1.09
     variability
    1.05
     heterogeneity
    1.03
     uncertainties
    1.02
     nonlinearity
    1.02
     distortions
    0.96
     variations
    0.95
    Act Density 0.096%

    No Known Activations