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

    Neuronpedia

    INDEX
    Explanations

    births

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imestamp
    -0.07
     Silk
    -0.07
    росс
    -0.07
     нек
    -0.07
     uncertainty
    -0.07
    扫码
    -0.07
     Skinner
    -0.07
    执勤
    -0.07
    *K
    -0.07
    啮
    -0.06
    POSITIVE LOGITS
    ads
    0.08
    cp
    0.07
     Building
    0.07
     Speaker
    0.06
    懿
    0.06
    新篇章
    0.06
    があれば
    0.06
     שלישי
    0.06
     diplomat
    0.06
     Introduction
    0.06
    Act Density 0.003%

    No Known Activations