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

    Neuronpedia

    INDEX
    Explanations

    say "quotation marks"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Curve
    -0.06
    ham
    -0.06
    řiv
    -0.06
     sausage
    -0.06
     tem
    -0.06
     choking
    -0.06
    territ
    -0.06
    -kit
    -0.06
     Martinez
    -0.06
     metrics
    -0.06
    POSITIVE LOGITS
     видно
    0.07
     Ciudad
    0.07
     chauff
    0.07
     лак
    0.06
    ovaných
    0.06
     投稿日
    0.06
    oubted
    0.06
     중심
    0.06
    ViewInit
    0.06
     عنوان
    0.06
    Act Density 0.001%

    No Known Activations