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

    Neuronpedia

    INDEX
    Explanations

    list item markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    राधना
    0.25
     Và
    0.23
     veins
    0.23
     condiments
    0.23
     、,
    0.22
    妗
    0.22
    াধ
    0.21
     skins
    0.21
     cvv
    0.21
     business
    0.20
    POSITIVE LOGITS
    दरअसल
    0.28
     Firstly
    0.27
    .
    0.27
     ஒவ்வொரு
    0.26
     सर्वप्रथम
    0.26
    żenie
    0.25
    この
    0.25
     Öncelikle
    0.25
     explique
    0.25
     pertama
    0.24
    Act Density 0.968%

    No Known Activations