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

    Neuronpedia

    INDEX
    Explanations

    following "Lady"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    т
    1.87
    ते
    1.77
    ง่าย
    1.74
     Sext
    1.69
    muş
    1.68
     bulky
    1.68
     innervation
    1.66
    migrations
    1.63
    Domic
    1.62
     Poké
    1.59
    POSITIVE LOGITS
    er
    2.63
     불구하고
    2.56
    ्यूब
    2.14
    ার
    2.05
     związ
    2.03
    перед
    2.03
     propuesta
    1.97
     negra
    1.97
    కి
    1.93
     fevereiro
    1.93
    Act Density 0.001%

    No Known Activations