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

    Neuronpedia

    INDEX
    Explanations

    numbers and codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kır
    -0.06
     bait
    -0.06
    ducer
    -0.05
     embr
    -0.05
     Cards
    -0.05
    expenses
    -0.05
     pessim
    -0.05
     republiky
    -0.05
    ابه
    -0.05
    ätz
    -0.05
    POSITIVE LOGITS
    /testify
    0.07
     Brooks
    0.07
     Davis
    0.07
    =default
    0.07
    .Wrap
    0.07
    备
    0.07
    �
    0.07
     Yours
    0.07
     свидетель
    0.07
     spy
    0.07
    Act Density 17.796%

    No Known Activations