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

    Neuronpedia

    INDEX
    Explanations

    Pluto

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /colors
    -0.07
    .mods
    -0.07
    coma
    -0.07
    Modes
    -0.07
     Processor
    -0.07
    有
    -0.07
     assembling
    -0.06
     büyük
    -0.06
     propensity
    -0.06
    ůj
    -0.06
    POSITIVE LOGITS
    See
    0.06
     STATIC
    0.06
     aren
    0.06
     circus
    0.06
     weren
    0.06
    UIImage
    0.06
     adversary
    0.06
     atop
    0.05
     couldn
    0.05
    [Test
    0.05
    Act Density 0.326%

    No Known Activations