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

    Neuronpedia

    INDEX
    Explanations

    small

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     liking
    -0.08
    уществ
    -0.08
     stumbling
    -0.08
     Maze
    -0.07
     maze
    -0.07
    urance
    -0.07
    共有
    -0.07
     dance
    -0.07
    .num
    -0.07
     partnering
    -0.07
    POSITIVE LOGITS
     approximation
    0.18
     approxim
    0.15
     negligible
    0.13
     neglected
    0.12
     neglect
    0.12
     Approx
    0.12
     neglig
    0.11
    Approx
    0.11
     regime
    0.11
     aproxim
    0.11
    Act Density 0.019%

    No Known Activations