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

    Neuronpedia

    INDEX
    Explanations

    product, project, market, database

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trapezium
    0.45
     sta
    0.44
     slowly
    0.43
     każdej
    0.42
    “
    0.42
     Nutt
    0.42
     noemen
    0.41
     funkcji
    0.41
     কয়েক
    0.40
     schreiben
    0.39
    POSITIVE LOGITS
    ज्ञानिक
    0.50
    ۹
    0.46
     άλλ
    0.44
     ۹
    0.43
     ९
    0.42
     QA
    0.42
     Annu
    0.42
     illness
    0.41
    )](
    0.41
     recue
    0.41
    Act Density 0.002%

    No Known Activations