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

    Neuronpedia

    INDEX
    Explanations

    oz

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gebn
    -0.07
    loomberg
    -0.06
    DownList
    -0.06
     depicted
    -0.06
    _phr
    -0.06
     Titanic
    -0.06
    鐵
    -0.06
    ckså
    -0.06
    --------------
    -0.06
    allon
    -0.06
    POSITIVE LOGITS
     temporada
    0.07
    [loc
    0.07
     relu
    0.06
    _CUSTOM
    0.06
     hues
    0.06
     Пом
    0.06
     몸
    0.06
     sigh
    0.06
    _ARCH
    0.06
     먹
    0.06
    Act Density 0.013%

    No Known Activations