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

    Neuronpedia

    INDEX
    Explanations

    planets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     planet
    -1.48
     continent
    -1.32
    planet
    -1.18
    RenderAtEndOf
    -1.09
     planets
    -1.09
     planète
    -1.02
    +#+#
    -1.02
    Planet
    -0.99
     Continent
    -0.97
     planeta
    -0.94
    POSITIVE LOGITS
    ,
    0.70
    .
    0.63
    ’
    0.61
    p
    0.61
     as
    0.60
    l
    0.58
    '
    0.58
    ser
    0.57
    ar
    0.57
    z
    0.57
    Act Density 0.059%

    No Known Activations