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

    Neuronpedia

    INDEX
    Explanations

    tarnished silver objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    妷
    0.43
    铁
    0.43
    Iron
    0.43
     Iron
    0.42
     IRON
    0.42
     შეუ
    0.42
    䄸
    0.42
     刺繍
    0.41
     சிவப்பு
    0.41
     철
    0.41
    POSITIVE LOGITS
     spoons
    0.67
     silver
    0.65
     spoon
    0.59
     tablespoons
    0.57
     teaspoons
    0.57
    Silver
    0.55
    silver
    0.55
     fiddle
    0.55
     tablespoon
    0.54
    银
    0.54
    Act Density 0.008%

    No Known Activations