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

    Neuronpedia

    INDEX
    Explanations

    thanks to / for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    1.01
    ல்
    0.97
     대해서
    0.97
    ترك
    0.87
     இருந்து
    0.86
     få
    0.85
    on
    0.83
    ка
    0.83
    τών
    0.82
    त्रि
    0.82
    POSITIVE LOGITS
    givings
    1.50
     gracias
    1.47
     thanks
    1.42
     grazie
    1.40
     graças
    1.33
    giving
    1.29
    Thanks
    1.28
     Thanks
    1.27
    thanks
    1.22
     díky
    1.18
    Act Density 0.012%

    No Known Activations