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

    Neuronpedia

    INDEX
    Explanations

    proposing to play

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Officer
    0.42
    ètes
    0.40
     yours
    0.40
     perfectly
    0.38
    Corn
    0.38
    ElementException
    0.37
    Compl
    0.37
    __."
    0.36
     compliments
    0.35
    ниях
    0.35
    POSITIVE LOGITS
     створи
    0.47
     созда
    0.42
     إنشاء
    0.42
    マット
    0.42
     oynuyoruz
    0.41
     ters
    0.41
     creazione
    0.41
     oyn
    0.41
     коммента
    0.41
     создания
    0.40
    Act Density 0.003%

    No Known Activations