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

    Neuronpedia

    INDEX
    Explanations

    iPaaS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Adel
    0.44
    ğından
    0.43
     प्रद
    0.43
     Але
    0.42
     أد
    0.41
    পরিব
    0.41
     الأد
    0.41
     schizophren
    0.41
    тету
    0.41
     বেকার
    0.40
    POSITIVE LOGITS
    ataan
    0.61
    attu
    0.59
    aan
    0.59
    aas
    0.56
    aat
    0.55
    aus
    0.55
     aas
    0.55
     AAS
    0.54
     AAP
    0.50
     aap
    0.50
    Act Density 0.002%

    No Known Activations