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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     figur
    -0.08
     onboard
    -0.07
    /navbar
    -0.07
    /not
    -0.07
     ETH
    -0.07
    AMS
    -0.07
    预留
    -0.07
     deducted
    -0.06
    LOW
    -0.06
     ****************************************************************
    -0.06
    POSITIVE LOGITS
    pi
    0.07
    椠
    0.07
    ∵
    0.07
    "):↵
    0.07
    Q
    0.07
    итель
    0.07
     •
    0.07
    erd
    0.07
    ש
    0.06
    质量管理
    0.06
    Act Density 0.000%

    No Known Activations