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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    verse
    -0.07
     الوز
    -0.07
    ╝
    -0.07
     Say
    -0.06
     وز
    -0.06
     písem
    -0.06
     tenure
    -0.06
    olesale
    -0.06
     leaked
    -0.06
     Haupt
    -0.06
    POSITIVE LOGITS
    0.06
     plist
    0.06
    261
    0.06
    ERVER
    0.06
    _suffix
    0.06
     시스템
    0.06
     metabol
    0.06
    .hist
    0.06
    _dem
    0.06
    则
    0.06
    Act Density 0.003%

    No Known Activations