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

    Neuronpedia

    INDEX
    Explanations

    different kinds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     at
    0.61
    တစ်ခု
    0.59
     five
    0.58
     the
    0.57
     là
    0.57
     one
    0.55
     lake
    0.55
     fifth
    0.54
     hiçbir
    0.54
     lisse
    0.54
    POSITIVE LOGITS
     různ
    0.89
    different
    0.76
     diferentes
    0.72
     Different
    0.72
     olika
    0.71
    不同的
    0.70
     مختلفة
    0.70
     különböző
    0.70
    Different
    0.70
     المختلفة
    0.69
    Act Density 0.080%

    No Known Activations