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

    Neuronpedia

    INDEX
    Explanations

    puff pastry and crust

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    0.70
    et
    0.63
    m
    0.61
    al
    0.59
    b
    0.59
    as
    0.57
    es
    0.56
    t
    0.54
    os
    0.53
    mets
    0.53
    POSITIVE LOGITS
     testify
    0.51
    ności
    0.47
     বরা
    0.46
     там
    0.46
     જેવા
    0.46
     níveis
    0.45
    ད
    0.45
    дэ
    0.44
     każdy
    0.43
    URNIZOR
    0.43
    Act Density 0.000%

    No Known Activations