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

    Neuronpedia

    INDEX
    Explanations

    code offsets and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zumindest
    0.44
     Barclays
    0.43
     Determ
    0.43
     utterance
    0.43
    了一种
    0.43
     ওরফে
    0.43
    အတ
    0.40
    تبار
    0.40
     énon
    0.40
    了一条
    0.40
    POSITIVE LOGITS
    шком
    0.46
    削減
    0.43
     unre
    0.43
     сопрово
    0.42
    тину
    0.41
     brewing
    0.41
    кости
    0.41
    ÍA
    0.40
     BENEFITS
    0.40
     extranjeros
    0.40
    Act Density 0.001%

    No Known Activations