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

    Neuronpedia

    INDEX
    Explanations

    add, find, start, execute, include

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.04
    m
    0.69
    ↵
    0.59
    c
    0.58
    h
    0.55
    q
    0.52
    ’
    0.51
    p
    0.50
    l
    0.49
    -
    0.49
    POSITIVE LOGITS
    ௐ
    0.73
     الأولى
    0.58
     një
    0.57
     رسمي
    0.55
    了一
    0.55
    0.55
    𝘥
    0.54
     as
    0.54
    ições
    0.54
     tại
    0.53
    Act Density 3.490%

    No Known Activations