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

    Neuronpedia

    INDEX
    Explanations

    chapter I roman numerals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     brasileiro
    0.61
    ai
    0.57
    د
    0.54
    illo
    0.54
    v
    0.53
    ails
    0.52
     a
    0.51
     ensino
    0.51
     fútbol
    0.50
    '
    0.50
    POSITIVE LOGITS
    ра
    0.66
     paperback
    0.62
     book
    0.57
    isbn
    0.57
    getBook
    0.57
    ла
    0.56
    ча
    0.55
     knih
    0.53
     Paperback
    0.53
    产
    0.53
    Act Density 0.283%

    No Known Activations