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

    Neuronpedia

    INDEX
    Explanations

    website URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     YAML
    0.61
     blurring
    0.59
     Imports
    0.56
     XGB
    0.56
     smoothed
    0.56
     Synthetic
    0.56
     debugging
    0.56
     Numerical
    0.55
     Poisson
    0.55
    Ĕ
    0.55
    POSITIVE LOGITS
    www
    2.25
     www
    1.88
    WWW
    1.16
    wwww
    1.11
    https
    1.05
    youtu
    0.97
     WWW
    0.92
     https
    0.89
    goo
    0.83
    twitter
    0.82
    Act Density 0.349%

    No Known Activations