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

    Neuronpedia

    INDEX
    Explanations

    vouchers and expiration dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hyper
    -0.08
    udes
    -0.08
    Primitive
    -0.08
     Aristotle
    -0.07
    sects
    -0.07
     জনগ
    -0.07
     whipping
    -0.07
    boys
    -0.07
     некоторое
    -0.07
    .hyper
    -0.07
    POSITIVE LOGITS
    期限
    0.10
    限定
    0.10
     redeem
    0.10
    兑换
    0.10
     redeemed
    0.10
    额度
    0.09
     redemption
    0.09
    余额
    0.09
     Lifetime
    0.09
     eligibility
    0.09
    Act Density 0.025%

    No Known Activations