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

    Neuronpedia

    INDEX
    Explanations

    let's define or imagine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Staying
    0.41
     garnet
    0.38
    များသည်
    0.38
     dudas
    0.38
     пе
    0.37
     рассказыва
    0.37
     getDescription
    0.37
    되었습니다
    0.36
     Learn
    0.36
     घोड़ा
    0.36
    POSITIVE LOGITS
     Punkte
    0.61
     points
    0.57
     X
    0.54
     punten
    0.54
    vectors
    0.53
     точек
    0.52
     x
    0.52
    三角形
    0.51
     matrices
    0.51
     ट्रायंगल
    0.51
    Act Density 0.016%

    No Known Activations