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

    Neuronpedia

    INDEX
    Explanations

    subject speaking verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    精度
    0.29
     PvP
    0.28
    由
    0.28
    避免
    0.28
     एहसास
    0.27
    需要
    0.27
     समझने
    0.27
    逐步
    0.26
    പ്പിച്ച്
    0.26
     Arrays
    0.26
    POSITIVE LOGITS
    ۔
    0.33
    。
    0.32
    «.
    0.30
     said
    0.30
    ।
    0.29
    。「
    0.29
     ayrıca
    0.29
    .«
    0.28
     tore
    0.28
     raccont
    0.28
    Act Density 0.034%

    No Known Activations