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

    Neuronpedia

    INDEX
    Explanations

    code keywords and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Бо
    0.46
    \
    0.44
     nghệ
    0.40
     Со
    0.40
    ﺍ
    0.39
     и
    0.38
     Бра
    0.38
     faisons
    0.38
    穸
    0.37
     Ба
    0.36
    POSITIVE LOGITS
    o
    0.84
    u
    0.57
    a
    0.54
    us
    0.52
    ة
    0.52
    op
    0.51
    و
    0.51
    ad
    0.50
    g
    0.50
    h
    0.49
    Act Density 0.472%

    No Known Activations