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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LG
    -0.07
    buy
    -0.07
    안
    -0.06
    ским
    -0.06
    TOTAL
    -0.06
    งแรก
    -0.06
    badge
    -0.06
     Spoj
    -0.06
    Deploy
    -0.06
    posted
    -0.06
    POSITIVE LOGITS
     winnings
    0.07
     accelerator
    0.06
    ´:
    0.06
     recovery
    0.06
     закін
    0.06
    .Can
    0.06
    challenge
    0.06
    」↵
    0.06
    END
    0.06
    _tweet
    0.06
    Act Density 0.002%

    No Known Activations