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

    Neuronpedia

    INDEX
    Explanations

    protective gear and clothing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tienes
    0.69
    ic
    0.60
    ри
    0.59
     ergibt
    0.58
    ע
    0.56
    তা
    0.56
    기
    0.55
    uskan
    0.54
    ுங்கள்
    0.54
    一个
    0.52
    POSITIVE LOGITS
     helmets
    0.72
     gloves
    0.66
     twisted
    0.65
     Padding
    0.63
    ⬮
    0.61
     resonated
    0.61
     resonates
    0.60
     scuba
    0.60
    শস্ত্র
    0.60
    getSimpleName
    0.59
    Act Density 0.085%

    No Known Activations