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

    Neuronpedia

    INDEX
    Explanations

    interest calculation and accrual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    පි
    0.43
    ༢
    0.43
    咡
    0.41
    пель
    0.40
    二百
    0.40
    യാണ്
    0.38
     فرن
    0.38
     小学
    0.38
    Regist
    0.37
    вропей
    0.37
    POSITIVE LOGITS
     hormone
    0.42
     sans
    0.39
     crass
    0.39
     weaker
    0.38
    shark
    0.38
    াপিত
    0.37
     TV
    0.37
    max
    0.36
    jakan
    0.36
    ഡിയോ
    0.36
    Act Density 0.002%

    No Known Activations