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

    Neuronpedia

    INDEX
    Explanations

    Now

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tập
    -0.06
     Kindle
    -0.06
    ![
    -0.06
     laminate
    -0.06
     trả
    -0.06
     Uhr
    -0.06
     Shak
    -0.06
     renown
    -0.06
     висок
    -0.06
    +%
    -0.06
    POSITIVE LOGITS
    Definitions
    0.07
    _appro
    0.07
    asier
    0.06
     positives
    0.06
     án
    0.06
    tem
    0.06
    ountries
    0.06
    _states
    0.06
    نام
    0.06
     destructive
    0.06
    Act Density 0.033%

    No Known Activations