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

    Neuronpedia

    INDEX
    Explanations

    experience

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mole
    -0.10
     вероят
    -0.09
     Carn
    -0.08
     probabilities
    -0.08
     Herbst
    -0.08
     delle
    -0.08
     вероятность
    -0.08
     приятно
    -0.08
     Dhar
    -0.07
    tris
    -0.07
    POSITIVE LOGITS
     работы
    0.09
    Years
    0.09
     роботи
    0.09
     زمینه
    0.08
     opged
    0.08
    Hours
    0.08
    Ports
    0.08
     sahibi
    0.08
     suficiente
    0.08
     زیادی
    0.08
    Act Density 0.027%

    No Known Activations