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

    Neuronpedia

    INDEX
    Explanations

    Because

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     öğret
    -0.07
     ним
    -0.06
     đi
    -0.06
    zbek
    -0.06
    wire
    -0.06
    庄
    -0.06
    ряду
    -0.06
    Contr
    -0.06
     nhiên
    -0.06
     المغ
    -0.06
    POSITIVE LOGITS
    market
    0.07
    .Since
    0.07
    -main
    0.07
    erner
    0.06
     sidel
    0.06
     Since
    0.06
    menin
    0.06
     txn
    0.06
    Emb
    0.06
    ns
    0.06
    Act Density 0.027%

    No Known Activations