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

    Neuronpedia

    INDEX
    Explanations

    dual graphs and triangulations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    evas
    -0.09
    験
    -0.08
    welcome
    -0.08
     enfin
    -0.07
    STATIC
    -0.07
     seductive
    -0.07
     ом
    -0.07
     dort
    -0.07
     نفس
    -0.07
    818
    -0.07
    POSITIVE LOGITS
     corres
    0.08
    िनिध
    0.08
     verwij
    0.08
     представляет
    0.08
     dual
    0.08
     đại
    0.08
    .imgur
    0.08
    dual
    0.08
     represents
    0.08
    对应
    0.08
    Act Density 0.008%

    No Known Activations