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

    Neuronpedia

    INDEX
    Explanations

    decades

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scented
    -0.09
     заказа
    -0.08
    úa
    -0.08
     Alloc
    -0.08
     snapped
    -0.08
     الفيديو
    -0.08
     выдел
    -0.08
     குறிப்ப
    -0.08
    setzung
    -0.08
    (stop
    -0.08
    POSITIVE LOGITS
     decades
    0.18
     years
    0.18
    Years
    0.17
     वर्षों
    0.16
    years
    0.16
     décadas
    0.15
     વર્ષ
    0.14
     century
    0.14
    年代
    0.14
     दशक
    0.13
    Act Density 0.042%

    No Known Activations