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

    Neuronpedia

    INDEX
    Explanations

    lists of nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    сі
    0.33
    ັງ
    0.32
    俻
    0.32
    ାନ
    0.32
     vált
    0.31
     và
    0.30
     redes
    0.30
     และ
    0.30
     ແລະ
    0.30
    ။
    0.30
    POSITIVE LOGITS
     بالإضافة
    0.38
    (!
    0.37
     ("
    0.35
     ('
    0.35
    ů
    0.33
    (""
    0.32
    (['
    0.32
     (!)
    0.31
    (["
    0.31
    
    0.31
    Act Density 0.216%

    No Known Activations