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

    Neuronpedia

    INDEX
    Explanations

    saving/writing files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    плення
    0.42
    дія
    0.37
    دیا
    0.37
    嫵
    0.37
     тощо
    0.36
    崤
    0.36
    ського
    0.35
     abiotic
    0.35
    CCOCC
    0.34
    oncé
    0.34
    POSITIVE LOGITS
    sanitize
    0.40
     dailySales
    0.38
    abhavena
    0.34
    清理
    0.33
     წლის
    0.33
     debugShow
    0.33
    aid
    0.33
    !");
    0.32
    sanity
    0.32
    has
    0.32
    Act Density 0.003%

    No Known Activations