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

    Neuronpedia

    INDEX
    Explanations

    Checksums and ID validation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Desired
    -0.09
     ultrap
    -0.08
     møter
    -0.08
     desired
    -0.08
     fẹ
    -0.08
     wished
    -0.08
     phủ
    -0.08
    desired
    -0.08
     Desired
    -0.07
    yň
    -0.07
    POSITIVE LOGITS
     checksum
    0.11
    checksum
    0.10
    验证码
    0.10
    规则
    0.09
    算法
    0.09
    Checksum
    0.09
    投注
    0.09
    期开奖结果
    0.08
     mystery
    0.08
     fraudulent
    0.08
    Act Density 0.003%

    No Known Activations