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

    Neuronpedia

    INDEX
    Explanations

    pone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sollten
    -0.07
     Granny
    -0.07
     Wal
    -0.06
    _VIRTUAL
    -0.06
     Brut
    -0.06
    BarButtonItem
    -0.06
    .Servlet
    -0.06
     NAV
    -0.06
    렴
    -0.06
    LogLevel
    -0.06
    POSITIVE LOGITS
     OE
    0.07
    -tm
    0.07
     的
    0.07
    ↵   ↵
    0.06
     circumstance
    0.06
     injecting
    0.06
    }/#{
    0.06
    まだ
    0.06
     length
    0.06
    ")},↵
    0.06
    Act Density 0.002%

    No Known Activations