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

    Neuronpedia

    INDEX
    Explanations

    legal torts and civil wrongs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ку
    0.68
    брав
    0.65
     отсут
    0.64
    𝘳
    0.63
    شانی
    0.63
    𝐤
    0.63
    <unused1726>
    0.62
    брать
    0.61
    𝘴
    0.61
    𝐠
    0.61
    POSITIVE LOGITS
    ল
    0.64
    ラ
    0.64
    ली
    0.58
    o
    0.57
     देखती
    0.55
     tuition
    0.54
    료
    0.53
    屉
    0.52
    등학교
    0.52
    ?
    0.52
    Act Density 0.001%

    No Known Activations