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

    Neuronpedia

    INDEX
    Explanations

    path definitions and URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     त्याग
    0.48
     prickly
    0.43
     Αγ
    0.43
    อฟ
    0.42
     tongs
    0.42
     Fleurit
    0.41
    deload
    0.41
     deuterium
    0.41
     Schilling
    0.41
     bushing
    0.41
    POSITIVE LOGITS
    urlpatterns
    0.88
     urlpatterns
    0.69
     path
    0.63
    path
    0.62
    url
    0.61
     URL
    0.58
     urls
    0.57
    urls
    0.56
     url
    0.55
    URL
    0.55
    Act Density 0.001%

    No Known Activations