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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     auss
    -0.06
    .Subscribe
    -0.06
     resid
    -0.06
    posix
    -0.06
     reven
    -0.06
    SceneManager
    -0.06
    Sampling
    -0.06
     Cla
    -0.06
     себе
    -0.06
     subsystem
    -0.06
    POSITIVE LOGITS
    审
    0.07
     ],↵↵
    0.07
    -so
    0.06
    翰
    0.06
     papers
    0.06
     potatoes
    0.06
    λης
    0.06
     Fist
    0.06
     mattered
    0.06
    Unsupported
    0.06
    Act Density 0.015%

    No Known Activations