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

    Neuronpedia

    INDEX
    Explanations

    scientific descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ulia
    -0.08
    "][
    -0.07
     moons
    -0.07
     -*-
    -0.07
    .hy
    -0.06
    high
    -0.06
    "},"
    -0.06
    jax
    -0.06
    )."
    -0.06
    정보
    -0.06
    POSITIVE LOGITS
     DEN
    0.07
     Carl
    0.07
     sia
    0.06
     ebenfalls
    0.06
    .swing
    0.06
     discreet
    0.06
     Buckingham
    0.06
    /release
    0.06
     Crimson
    0.06
     更
    0.06
    Act Density 0.202%

    No Known Activations