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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    apsible
    -0.06
    Modal
    -0.06
    ンジ
    -0.06
     Odds
    -0.06
    Submit
    -0.06
    -box
    -0.06
    .market
    -0.06
     dostup
    -0.06
    วาม
    -0.06
    Ком
    -0.06
    POSITIVE LOGITS
    couldn
    0.07
     состоит
    0.06
    xiety
    0.06
    elen
    0.06
     सरक
    0.06
    uchs
    0.06
    もし
    0.06
    iệng
    0.06
    ái
    0.06
     대해서
    0.06
    Act Density 0.015%

    No Known Activations