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

    Neuronpedia

    INDEX
    Explanations

    say "d"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     de
    0.78
    de
    0.50
     De
    0.46
    De
    0.44
    <0xA4>
    0.41
     दे
    0.39
     де
    0.37
     DE
    0.34
    ủa
    0.34
     suatu
    0.34
    POSITIVE LOGITS
     d
    1.55
     д
    1.29
     د
    1.22
     द
    1.09
    <0x93>
    1.09
     দ
    1.01
    d
    1.01
    ด
    0.92
    ｄ
    0.92
     દ
    0.77
    Act Density 0.001%

    No Known Activations