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

    Neuronpedia

    INDEX
    Explanations

    Citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     paid
    -0.07
    .numpy
    -0.07
     danych
    -0.07
     NFC
    -0.07
    (gcf
    -0.07
     wur
    -0.07
     suç
    -0.07
     jpeg
    -0.07
    (coder
    -0.07
    )init
    -0.07
    POSITIVE LOGITS
     pro
    0.06
    боль
    0.06
     т
    0.06
    淚
    0.06
    -turn
    0.06
    定期
    0.06
    新一轮
    0.06
     turns
    0.06
    ">';↵
    0.06
     bre
    0.06
    Act Density 0.043%

    No Known Activations