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

    Neuronpedia

    INDEX
    Explanations

    constructive communication advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     கரிம
    0.44
     World
    0.40
     raster
    0.39
     raw
    0.38
     Chromium
    0.38
    OS
    0.38
     IPv
    0.38
     获取
    0.38
     pickled
    0.38
     gzip
    0.38
    POSITIVE LOGITS
     politely
    0.90
     diplom
    0.66
     polite
    0.64
     persuas
    0.59
     amicable
    0.56
     объяснить
    0.55
     diplomatic
    0.54
     worded
    0.52
     amiable
    0.52
    ampaikan
    0.50
    Act Density 0.264%

    No Known Activations