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

    Neuronpedia

    INDEX
    Explanations

    approximate numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estimates
    0.84
     ESTIM
    0.83
    估计
    0.82
    Estim
    0.82
     estimate
    0.82
     estimated
    0.81
     Estimated
    0.80
     Estimates
    0.79
     estim
    0.76
    estimates
    0.75
    POSITIVE LOGITS
     nearly
    1.18
     Nearly
    1.09
    Nearly
    1.08
    nearly
    1.02
     bijna
    0.96
     почти
    0.95
     майже
    0.91
     almost
    0.90
    Almost
    0.86
     quase
    0.86
    Act Density 0.085%

    No Known Activations