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

    Neuronpedia

    INDEX
    Explanations

    describing properties or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    드가
    0.49
    베
    0.48
    प्र
    0.47
    만
    0.47
    álló
    0.47
    දය
    0.46
    əm
    0.45
     पंचायत
    0.45
    みの
    0.45
    复合
    0.45
    POSITIVE LOGITS
     Lui
    0.45
     metri
    0.44
     Philips
    0.42
     stabilit
    0.41
     ট্যাব
    0.41
     своє
    0.41
    の研究
    0.40
     marchand
    0.39
     encontrada
    0.39
     FON
    0.39
    Act Density 0.002%

    No Known Activations