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

    Neuronpedia

    INDEX
    Explanations

    this is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     কেবলমাত্র
    0.50
    瀣
    0.48
     دیگر
    0.48
    Ფ
    0.48
     Wirtschaft
    0.47
    Ｎ
    0.47
    Ꭻ
    0.47
    ОР
    0.47
    Ц
    0.47
    ⟣
    0.47
    POSITIVE LOGITS
     peppers
    0.55
     used
    0.53
     expresses
    0.50
     親
    0.50
     distrust
    0.48
     generated
    0.48
     spying
    0.48
     accus
    0.47
     scouting
    0.47
     princes
    0.47
    Act Density 0.000%

    No Known Activations