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

    Neuronpedia

    INDEX
    Explanations

    introduction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vue
    -0.07
    _vocab
    -0.06
     trusted
    -0.06
     Mongo
    -0.06
     associated
    -0.06
     mischief
    -0.06
     welfare
    -0.06
    ups
    -0.06
     Investor
    -0.06
     \%
    -0.06
    POSITIVE LOGITS
     produits
    0.07
    �ng
    0.07
     duż
    0.07
    explicit
    0.07
     employing
    0.07
     BOOL
    0.07
     bulunuyor
    0.06
     admit
    0.06
     urlpatterns
    0.06
    altitude
    0.06
    Act Density 0.011%

    No Known Activations