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

    Neuronpedia

    INDEX
    Explanations

    now

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .contract
    -0.07
     cav
    -0.06
    .annotation
    -0.06
    υχ
    -0.06
     narrator
    -0.06
    ,true
    -0.06
    .gradient
    -0.06
     IList
    -0.06
    _{
    -0.06
     determined
    -0.06
    POSITIVE LOGITS
    ادل
    0.07
     Thái
    0.06
    Often
    0.06
     ساعت
    0.06
    ToEnd
    0.06
    porto
    0.06
     رق
    0.06
     posledních
    0.06
     Pelosi
    0.06
    ãeste
    0.06
    Act Density 0.013%

    No Known Activations