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

    Neuronpedia

    INDEX
    Explanations

    option 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     உருவாக
    0.46
     kin
    0.46
     პრო
    0.45
     কয়েকটি
    0.45
     Soils
    0.45
     altın
    0.44
    alt
    0.44
     rafters
    0.44
     வடிவமை
    0.43
     অসহায়
    0.43
    POSITIVE LOGITS
    ست
    0.46
    כון
    0.45
    ༨
    0.44
    ED
    0.44
    gub
    0.44
    伶
    0.44
    جست
    0.43
    荼
    0.43
    ร
    0.43
    ก
    0.42
    Act Density 0.107%

    No Known Activations