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

    Neuronpedia

    INDEX
    Explanations

    the noun following

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ات
    1.54
    ς
    1.29
    sächlich
    1.23
    ൦
    1.22
    0
    1.19
    ง
    1.18
    คุณ
    1.13
    ់
    1.11
    ても
    1.10
    s
    1.08
    POSITIVE LOGITS
     dette
    0.98
    ни
    0.93
    io
    0.89
     européen
    0.89
     proie
    0.88
    imagens
    0.88
     hun
    0.88
    se
    0.87
    BER
    0.86
     Andean
    0.86
    Act Density 0.212%

    No Known Activations