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

    Neuronpedia

    INDEX
    Explanations

    certain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tow
    -0.07
     advanced
    -0.07
     kW
    -0.07
     listOf
    -0.07
    粗
    -0.07
    ReadOnly
    -0.06
    大赛
    -0.06
     kz
    -0.06
    度过
    -0.06
     Ole
    -0.06
    POSITIVE LOGITS
     admit
    0.07
    忑
    0.07
     Ces
    0.07
    xCF
    0.07
    息
    0.07
     возможно
    0.07
    +$
    0.07
    血压
    0.07
    ]+$
    0.07
    柏
    0.06
    Act Density 0.050%

    No Known Activations