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

    Neuronpedia

    INDEX
    Explanations

    BERT models and NLP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     William
    -0.07
     possession
    -0.07
    旗
    -0.07
     jouent
    -0.07
     സംസ്ഥാന
    -0.07
     skilled
    -0.07
     Ember
    -0.07
    	at
    -0.07
     ladder
    -0.07
     zut
    -0.07
    POSITIVE LOGITS
    (fields
    0.09
    -like
    0.09
     otu
    0.08
     δω
    0.08
    Shop
    0.08
     fucking
    0.08
     Barnes
    0.08
     ove
    0.08
     Orchard
    0.07
     obligatory
    0.07
    Act Density 0.009%

    No Known Activations