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

    Neuronpedia

    INDEX
    Explanations

    amazon clothing descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ...
    0.61
     v
    0.58
     $
    0.58
     ...,
    0.57
    0.57
     Ν
    0.56
     til
    0.56
     giant
    0.56
     N
    0.55
     нова
    0.55
    POSITIVE LOGITS
     garments
    1.15
     sweatshirts
    1.06
    穿着
    1.03
    Clothing
    1.02
     Clothing
    0.98
     clothing
    0.98
     sweatshirt
    0.96
     prendas
    0.95
    เสื้อ
    0.95
     garment
    0.94
    Act Density 0.002%

    No Known Activations