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

    Neuronpedia

    INDEX
    Explanations

    say "bucket"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     serm
    -0.06
    长度
    -0.06
    ере
    -0.06
     rop
    -0.06
     побач
    -0.06
     unwrap
    -0.06
     vistas
    -0.06
    决定
    -0.06
    Optimizer
    -0.06
    .static
    -0.06
    POSITIVE LOGITS
    _LAT
    0.07
    .getDate
    0.06
    ắm
    0.06
     Telescope
    0.06
     Kıs
    0.06
     genellikle
    0.06
     основном
    0.06
     terrorists
    0.06
    spell
    0.06
    apgolly
    0.06
    Act Density 0.001%

    No Known Activations