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

    Neuronpedia

    INDEX
    Explanations

    fade

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    —or
    -0.08
    [thread
    -0.07
     بای
    -0.07
    っく
    -0.07
    лоч
    -0.07
    Cell
    -0.07
     chains
    -0.06
     či
    -0.06
    .left
    -0.06
     Cli
    -0.06
    POSITIVE LOGITS
     fade
    0.11
    fade
    0.10
     Fade
    0.09
     faded
    0.08
    lásil
    0.07
     fading
    0.07
    дем
    0.07
     fades
    0.06
     radiation
    0.06
     grazing
    0.06
    Act Density 0.002%

    No Known Activations