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

    Neuronpedia

    INDEX
    Explanations

    technical terms and proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ق
    0.56
    存在
    0.48
    वह
    0.47
    قبل
    0.46
     puffy
    0.45
    د
    0.45
    、
    0.43
    人に
    0.43
    含ま
    0.42
    目的
    0.42
    POSITIVE LOGITS
    টাল
    0.51
     Ambrose
    0.49
     hrvats
    0.49
     চাহিয়া
    0.49
     réduit
    0.48
    打击
    0.48
     заклю
    0.48
     książ
    0.48
    可谓
    0.47
    აში
    0.46
    Act Density 0.000%

    No Known Activations