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

    Neuronpedia

    INDEX
    Explanations

    area machine shops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused2123>
    0.43
     Ayrıca
    0.42
    决策
    0.42
    匽
    0.42
     należy
    0.41
     Quand
    0.41
     Nate
    0.41
     മറ്റ്
    0.41
     Outcomes
    0.40
    겜
    0.40
    POSITIVE LOGITS
     sale
    0.48
    ：
    0.47
    出售
    0.47
     распро
    0.46
     продажи
    0.45
    image
    0.44
    ាង
    0.43
     drooping
    0.43
    abol
    0.43
     penjualan
    0.43
    Act Density 0.006%

    No Known Activations