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

    Neuronpedia

    INDEX
    Explanations

    percentage change and growth rates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {
    0.49
     multiplying
    0.49
     multiplication
    0.47
     spouse
    0.45
    ल्व
    0.44
     $.
    0.42
     $:
    0.42
     payments
    0.41
     }{
    0.41
    ﺎ
    0.41
    POSITIVE LOGITS
     Veränderungen
    0.46
     Trends
    0.45
     কোনও
    0.44
    变革
    0.43
    车站
    0.43
     Sequelize
    0.42
    细胞
    0.42
     Railway
    0.42
    ImageBeforeText
    0.41
    沚
    0.41
    Act Density 0.006%

    No Known Activations