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

    Neuronpedia

    INDEX
    Explanations

    much, considerably, significantly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     บ้าง
    0.82
    บ้าง
    0.73
     kadang
    0.70
     Sometimes
    0.70
    极致
    0.67
     sometimes
    0.66
    Sometimes
    0.66
    あり
    0.65
    sometimes
    0.64
    บาง
    0.64
    POSITIVE LOGITS
     much
    4.37
    Much
    4.01
    much
    3.95
     Much
    3.80
     MUCH
    3.79
     mucho
    3.57
     considerably
    3.15
     гораздо
    3.05
     significantly
    3.04
     znacznie
    2.99
    Act Density 0.466%

    No Known Activations