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

    Neuronpedia

    INDEX
    Explanations

    summarize long text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     respuestas
    0.44
     answering
    0.43
     puisi
    0.42
     menjawab
    0.42
     translations
    0.41
     kaikki
    0.41
     poetry
    0.41
     جائز
    0.41
    ละคร
    0.41
     semua
    0.41
    POSITIVE LOGITS
     text
    0.86
     текста
    0.83
    text
    0.82
    文本
    0.78
    Text
    0.75
     texts
    0.73
     texte
    0.73
     текст
    0.73
     texto
    0.71
     textes
    0.69
    Act Density 0.016%

    No Known Activations