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

    Neuronpedia

    INDEX
    Explanations

    basic, limited, or traditional qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     аксессу
    0.89
     фирмы
    0.82
    ﻼ
    0.82
     еще
    0.79
     врач
    0.79
     выступа
    0.79
     buen
    0.78
     высо
    0.77
    лым
    0.77
     ویژگی
    0.77
    POSITIVE LOGITS
    lessly
    0.84
    server
    0.81
     August
    0.81
    work
    0.78
    in
    0.75
    justice
    0.73
    d
    0.73
    sw
    0.72
    l
    0.71
    he
    0.71
    Act Density 0.003%

    No Known Activations