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

    Neuronpedia

    INDEX
    Explanations

    jewels and gems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Grace
    0.77
    Giving
    0.74
    жи
    0.74
    ուս
    0.73
    克斯
    0.72
    ној
    0.71
    naires
    0.71
    C
    0.70
    S
    0.70
    سم
    0.69
    POSITIVE LOGITS
     jewel
    1.42
     jewels
    1.40
     gems
    1.37
     gem
    1.29
     in
    1.20
     jewelry
    1.08
     gemstone
    1.06
     sapphire
    1.06
     gemstones
    1.04
     Gem
    1.03
    Act Density 0.038%

    No Known Activations