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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Author
    -0.07
    UBLISH
    -0.06
    薮
    -0.06
     kaps
    -0.06
     startPos
    -0.06
    établ
    -0.06
     getOrder
    -0.06
     suç
    -0.06
    פט
    -0.06
    ☂
    -0.06
    POSITIVE LOGITS
     октября
    0.07
    马拉
    0.06
    Extras
    0.06
     kayak
    0.06
    upuncture
    0.06
     Rica
    0.06
    公积金
    0.06
    final
    0.06
    >())↵
    0.06
     Люб
    0.06
    Act Density 0.015%

    No Known Activations