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

    Neuronpedia

    INDEX
    Explanations

    In summary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Madrid
    0.46
     era
    0.45
     essence
    0.43
    argu
    0.41
    ଭ
    0.40
     başta
    0.40
     actualidad
    0.39
     Switzerland
    0.39
     Geneva
    0.38
    Madrid
    0.38
    POSITIVE LOGITS
     summaries
    0.53
    summar
    0.52
    widgetTo
    0.50
     summarizing
    0.50
     SUMMARY
    0.49
     Summar
    0.49
     summarise
    0.48
     щодо
    0.48
     summarize
    0.48
     summarizes
    0.47
    Act Density 0.004%

    No Known Activations