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

    Neuronpedia

    INDEX
    Explanations

    books and magazines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cac
    0.38
    sar
    0.37
    ū
    0.37
     Sabre
    0.36
     px
    0.36
    Sap
    0.36
    зм
    0.35
     سرخ
    0.34
    sap
    0.34
    lé
    0.34
    POSITIVE LOGITS
     పుస్త
    0.67
     magazines
    0.65
     publishers
    0.64
    书籍
    0.64
     paperback
    0.64
     periodicals
    0.63
     Magazines
    0.63
     libros
    0.63
     पुस्तक
    0.61
    杂志
    0.61
    Act Density 0.024%

    No Known Activations