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

    Neuronpedia

    INDEX
    Explanations

    research reproducibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    详细了解
    -0.07
     populate
    -0.07
     $("#
    -0.06
     conservation
    -0.06
    稚
    -0.06
    ioms
    -0.06
    nemonic
    -0.06
     SON
    -0.06
    /libs
    -0.06
     whoever
    -0.06
    POSITIVE LOGITS
    :^
    0.07
    油烟
    0.07
     eyebrow
    0.07
    lsru
    0.07
    Issues
    0.06
     Suppress
    0.06
     stir
    0.06
    骗局
    0.06
    而后
    0.06
    กระท
    0.06
    Act Density 0.027%

    No Known Activations