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

    Neuronpedia

    INDEX
    Explanations

    reading passage questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pics
    0.47
     Interiors
    0.44
    ッチ
    0.44
     sexy
    0.43
     purged
    0.43
     параметры
    0.42
    無い
    0.42
    πί
    0.42
     Designated
    0.42
     لیست
    0.42
    POSITIVE LOGITS
     paragraph
    0.92
    paragraph
    0.81
     Paragraph
    0.78
     paragraphs
    0.68
     article
    0.66
    文中
    0.66
     passage
    0.64
    Paragraph
    0.63
     paragra
    0.62
     párrafo
    0.60
    Act Density 0.034%

    No Known Activations