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

    Neuronpedia

    INDEX
    Explanations

    increase or new

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     socio
    0.55
     stakeholder
    0.50
     valeurs
    0.49
     cosine
    0.49
     socioeconomic
    0.49
     financiero
    0.48
     ventajas
    0.48
     globale
    0.47
     finans
    0.47
     valori
    0.47
    POSITIVE LOGITS
     новые
    0.51
    更多的
    0.48
     بیشتری
    0.46
     новых
    0.43
     nuovi
    0.42
    増や
    0.42
    新しい
    0.42
     نئی
    0.42
     المزيد
    0.41
     neue
    0.41
    Act Density 0.087%

    No Known Activations