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

    Neuronpedia

    INDEX
    Explanations

    competition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .gamma
    -0.08
    ствовать
    -0.07
    anship
    -0.07
     felt
    -0.07
    Bet
    -0.07
    Assignment
    -0.07
    好不容易
    -0.06
    ()})↵
    -0.06
    pliant
    -0.06
     donate
    -0.06
    POSITIVE LOGITS
    չ
    0.07
    荒
    0.07
    会见
    0.07
    工会
    0.07
    (main
    0.07
     Boyd
    0.07
    冈
    0.06
    mins
    0.06
     desp
    0.06
    green
    0.06
    Act Density 0.038%

    No Known Activations