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

    Neuronpedia

    INDEX
    Explanations

    special conditions or qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    țiilor
    0.51
    ographique
    0.43
     образом
    0.42
    upu
    0.42
    recen
    0.41
    posto
    0.41
     organizacji
    0.41
    旅遊
    0.40
     possa
    0.40
     sats
    0.40
    POSITIVE LOGITS
    ر
    0.43
    یل
    0.42
     whimsical
    0.41
     cuyas
    0.41
    깁
    0.41
    By
    0.41
    ილ
    0.41
     bằng
    0.40
    𝑰
    0.40
    იან
    0.40
    Act Density 0.000%

    No Known Activations