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

    Neuronpedia

    INDEX
    Explanations

    short/brief

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _does
    -0.08
    >To
    -0.08
    쐬
    -0.07
     laser
    -0.06
     persever
    -0.06
     Vir
    -0.06
    暑
    -0.06
     recipe
    -0.06
    \Page
    -0.06
    /site
    -0.06
    POSITIVE LOGITS
    헴
    0.08
     فيما
    0.08
     rides
    0.07
    =item
    0.07
    均衡
    0.07
    赆
    0.07
    آل
    0.07
     ViewBag
    0.07
    リフォ
    0.06
    inement
    0.06
    Act Density 0.027%

    No Known Activations