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

    Neuronpedia

    INDEX
    Explanations

    fitted and equipped for clothing, kitchens, or furnishings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.80
    ام
    0.70
    ak
    0.69
    am
    0.68
    r
    0.68
    ر
    0.68
    ad
    0.63
    qui
    0.63
    dır
    0.63
    на
    0.63
    POSITIVE LOGITS
    urit
    0.59
     பரு
    0.57
    보험
    0.56
     سینٹی
    0.55
    usetts
    0.55
     جارہ
    0.54
    ާތ
    0.54
    风险
    0.54
    िख
    0.53
     Вя
    0.53
    Act Density 0.001%

    No Known Activations