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

    Neuronpedia

    INDEX
    Explanations

    more capable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oras
    0.52
    ল
    0.48
     Penet
    0.48
    ads
    0.47
     ह
    0.46
    osm
    0.45
    inputs
    0.45
    oglobin
    0.45
    roits
    0.44
    퓰
    0.44
    POSITIVE LOGITS
     resilient
    0.60
     пти
    0.49
     sepeda
    0.44
    الف
    0.44
     menjaga
    0.43
     vocal
    0.43
     rés
    0.43
     чисто
    0.43
     criando
    0.43
    зия
    0.43
    Act Density 0.001%

    No Known Activations