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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _bus
    -0.07
    czas
    -0.06
     Rek
    -0.06
     vej
    -0.06
     trang
    -0.06
     ay
    -0.06
     官
    -0.06
     země
    -0.06
     Netz
    -0.06
     UX
    -0.06
    POSITIVE LOGITS
    所以
    0.07
     satur
    0.06
    �습니다
    0.06
    <IM
    0.06
    _ELEMENTS
    0.06
    !!!
    0.06
    šak
    0.06
     evidently
    0.06
     scenic
    0.06
     Cao
    0.06
    Act Density 0.008%

    No Known Activations