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

    Neuronpedia

    INDEX
    Explanations

    research or work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     automobil
    0.48
     hearers
    0.48
     principaux
    0.47
     preachers
    0.45
    ংলার
    0.45
     berharap
    0.45
     myogenic
    0.44
     liber
    0.44
    ัคร
    0.44
     yoki
    0.44
    POSITIVE LOGITS
    Телефон
    0.46
     Дело
    0.44
    China
    0.43
     Фото
    0.42
    题
    0.42
    工作
    0.42
    特定
    0.41
     На
    0.41
     специфи
    0.41
    角度
    0.40
    Act Density 0.001%

    No Known Activations