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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ')[
    -0.08
     resistencia
    -0.08
    ичес
    -0.08
     distancia
    -0.07
    ер
    -0.07
     مقا
    -0.07
     fascin
    -0.07
    ующим
    -0.07
     drums
    -0.07
    Resistance
    -0.07
    POSITIVE LOGITS
     இல்லை
    0.09
     juist
    0.09
    还是
    0.08
    等等
    0.08
    kah
    0.08
    其次
    0.08
     కాదు
    0.08
    ndata
    0.08
     नाही
    0.08
     tampoco
    0.08
    Act Density 0.085%

    No Known Activations