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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -im
    -0.07
    [m
    -0.07
    .perform
    -0.07
    .Ptr
    -0.07
    _Find
    -0.06
    (Tile
    -0.06
     |>
    -0.06
    Sm
    -0.06
    سر
    -0.06
    _tile
    -0.06
    POSITIVE LOGITS
     healthier
    0.07
     THEY
    0.06
     Judaism
    0.06
    一度
    0.06
     tonumber
    0.06
     متر
    0.06
     proport
    0.06
    버전
    0.06
     PrintWriter
    0.05
     каждого
    0.05
    Act Density 0.030%

    No Known Activations