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

    Neuronpedia

    INDEX
    Explanations

    code and time deltas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Browse
    -0.08
     बे
    -0.08
     FAMILY
    -0.08
     bingo
    -0.08
     Dane
    -0.07
     masterm
    -0.07
     zig
    -0.07
     bankrupt
    -0.07
     kinders
    -0.07
    .banner
    -0.07
    POSITIVE LOGITS
    _elapsed
    0.13
     timestep
    0.13
     elapsed
    0.11
    Elapsed
    0.11
    elapsed
    0.11
    .timedelta
    0.11
     시간을
    0.11
    .elapsed
    0.10
    (time
    0.10
    (milliseconds
    0.10
    Act Density 0.003%

    No Known Activations