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

    Neuronpedia

    INDEX
    Explanations

    craft and making

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    0.92
    3
    0.86
    of
    0.83
    .
    0.75
    テ
    0.74
     دکتر
    0.72
    n
    0.70
    6
    0.67
    SI
    0.67
    4
    0.67
    POSITIVE LOGITS
     artisans
    1.20
     изделия
    1.06
     bracelets
    1.02
     handicrafts
    1.00
     sarees
    1.00
     craftsmen
    0.97
     artesan
    0.95
     Handmade
    0.94
     artisan
    0.93
     craftsmanship
    0.92
    Act Density 0.062%

    No Known Activations