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

    Neuronpedia

    INDEX
    Explanations

    maketitle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Бы
    2.07
    Глав
    1.96
    იკ
    1.85
     DbSet
    1.71
     tengas
    1.67
    Ле
    1.67
    おり
    1.67
     chained
    1.67
     reasoning
    1.66
    機関
    1.64
    POSITIVE LOGITS
    te
    2.15
    entesque
    1.91
     quartile
    1.74
    喹
    1.69
    lllll
    1.69
     Eigent
    1.65
    tedir
    1.64
    llllll
    1.63
    िके
    1.63
    to
    1.61
    Act Density 0.000%

    No Known Activations