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

    Neuronpedia

    INDEX
    Explanations

    end of sentence/thought

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    1.23
    im
    1.05
    ↵↵
    1.02
    ia
    1.00
    ov
    0.95
    ot
    0.95
    iy
    0.93
    ਾ
    0.91
     (
    0.90
    elves
    0.89
    POSITIVE LOGITS
     sabiduría
    1.08
    Кроме
    1.06
    İlk
    1.04
    𝐬
    1.02
     quark
    1.00
    Кто
    1.00
    Ни
    0.99
    Примеча
    0.99
    Czas
    0.99
     Και
    0.98
    Act Density 0.163%

    No Known Activations