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

    Neuronpedia

    INDEX
    Explanations

    carbon atoms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অস্ত্র
    0.43
    िल्स
    0.43
    衮
    0.42
    なら
    0.42
     베
    0.40
    钟
    0.39
    ार्म
    0.38
     Festivals
    0.38
     Пар
    0.38
    емое
    0.37
    POSITIVE LOGITS
    renew
    0.44
     serez
    0.44
    GFP
    0.44
     subl
    0.43
     pomiędzy
    0.43
     plumage
    0.42
     usare
    0.42
     把
    0.42
    énées
    0.41
     mobilize
    0.41
    Act Density 0.003%

    No Known Activations