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

    Neuronpedia

    INDEX
    Explanations

    titles and family members

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alcoved
    0.46
    名称
    0.44
     parquet
    0.43
    font
    0.42
     gamut
    0.42
    century
    0.40
    Its
    0.40
     disabilities
    0.40
    IPv
    0.39
    🗾
    0.38
    POSITIVE LOGITS
     Mrs
    1.04
     Aunt
    0.94
     Grandma
    0.89
    Mrs
    0.88
     Uncle
    0.88
     মিসেস
    0.82
     श्रीमती
    0.81
     Mama
    0.80
     Grandpa
    0.80
     Granny
    0.79
    Act Density 0.013%

    No Known Activations