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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     addiction
    -0.08
    ธา
    -0.07
     graf
    -0.07
    dba
    -0.07
    まだまだ
    -0.07
    部部长
    -0.07
    asyarak
    -0.06
    货源
    -0.06
    接手
    -0.06
    打法
    -0.06
    POSITIVE LOGITS
     Murder
    0.07
     preserving
    0.07
     buzz
    0.07
    produ
    0.07
     specialised
    0.06
     escrit
    0.06
     prec
    0.06
    unordered
    0.06
     divides
    0.06
     Carousel
    0.06
    Act Density 0.027%

    No Known Activations