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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alus
    -0.08
    Moment
    -0.07
    Swap
    -0.07
    Simple
    -0.07
     Rox
    -0.07
    bout
    -0.07
    middlewares
    -0.06
    gger
    -0.06
    ani
    -0.06
    Transform
    -0.06
    POSITIVE LOGITS
    eating
    0.06
     renk
    0.06
    .Utils
    0.06
     세상
    0.06
    (fout
    0.06
     куп
    0.06
     prostě
    0.06
     QE
    0.06
    AUSE
    0.06
     خارج
    0.06
    Act Density 0.038%

    No Known Activations