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

    Neuronpedia

    INDEX
    Explanations

    receipt of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    리면
    0.96
    ສາມາດ
    0.91
     سایټ
    0.90
    geoType
    0.90
    も含
    0.86
    targetReference
    0.86
    رے
    0.85
    はなく
    0.85
    يك
    0.84
    وي
    0.84
    POSITIVE LOGITS
     of
    1.45
    d
    1.41
    f
    1.34
     from
    1.33
    m
    1.28
    b
    1.23
    z
    1.23
     on
    1.19
     [
    1.14
    ↵↵
    1.11
    Act Density 2.027%

    No Known Activations