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

    Neuronpedia

    INDEX
    Explanations

    categorization and listing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ultrast
    0.50
    ات
    0.46
    תו
    0.46
    тельство
    0.45
    товая
    0.44
    inology
    0.41
    тельства
    0.40
     crustaceans
    0.40
    راث
    0.39
     tailor
    0.39
    POSITIVE LOGITS
     résultat
    0.47
     نتی
    0.47
     agréable
    0.47
     Aloha
    0.45
     COS
    0.44
     Italie
    0.43
     commuters
    0.43
    വി
    0.43
     nécessaire
    0.43
    जिब
    0.43
    Act Density 0.004%

    No Known Activations