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

    Neuronpedia

    INDEX
    Explanations

    text comprehension and summarization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wann
    0.75
    ueva
    0.70
     Giveaway
    0.69
     અહીં
    0.67
     coordinates
    0.65
    घर
    0.65
     ഇപ്പോ
    0.64
     मानने
    0.64
     produzir
    0.63
     usuario
    0.63
    POSITIVE LOGITS
     texts
    1.39
     text
    1.21
     textos
    1.16
     Texts
    1.14
     texto
    1.11
    文本
    1.09
    Texts
    1.09
     passages
    1.08
    テキスト
    1.08
     textes
    1.07
    Act Density 0.405%

    No Known Activations