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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     towns
    -0.07
     warrior
    -0.07
     Saf
    -0.07
    OLL
    -0.07
    waters
    -0.07
     ढ
    -0.07
    ادي
    -0.06
    圈
    -0.06
    status
    -0.06
     sands
    -0.06
    POSITIVE LOGITS
    алов
    0.06
    еся
    0.06
    ічний
    0.06
     principle
    0.06
    技術
    0.06
     clases
    0.06
     využí
    0.06
    иты
    0.05
     bureaucratic
    0.05
    \Requests
    0.05
    Act Density 0.009%

    No Known Activations