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

    Neuronpedia

    INDEX
    Explanations

    version numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ariate
    -0.07
    -'.$
    -0.06
    _FIRE
    -0.06
    _site
    -0.06
     spre
    -0.06
    琴
    -0.06
    .keras
    -0.06
    енка
    -0.06
    ραση
    -0.06
     irregular
    -0.06
    POSITIVE LOGITS
     amount
    0.07
    ควร
    0.07
     accustomed
    0.06
     Instantiate
    0.06
     electorate
    0.06
     Fifty
    0.06
     trest
    0.06
    astle
    0.06
     voted
    0.06
    @(
    0.06
    Act Density 0.005%

    No Known Activations