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

    Neuronpedia

    INDEX
    Explanations

    displaysspectrumshowing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     konkur
    0.55
    عمال
    0.51
    螌
    0.51
     numai
    0.50
     prochaine
    0.46
    勖
    0.46
    秫
    0.46
    annuation
    0.46
    喟
    0.46
     dekor
    0.46
    POSITIVE LOGITS
     x
    0.63
     i
    0.60
     e
    0.58
    =
    0.54
    start
    0.52
     metabolized
    0.52
     I
    0.52
     start
    0.52
     id
    0.51
     triglycerides
    0.51
    Act Density 0.001%

    No Known Activations