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

    Neuronpedia

    INDEX
    Explanations

    American or English followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ه
    1.60
    tiden
    1.53
    ن
    1.51
    ം
    1.50
    ের
    1.48
    пример
    1.48
    ات
    1.37
    ானா
    1.37
    ként
    1.34
    لية
    1.34
    POSITIVE LOGITS
    ic
    1.74
    ası
    1.64
    ll
    1.59
    th
    1.50
    ln
    1.50
    row
    1.45
    ning
    1.45
    an
    1.40
    lar
    1.40
    nt
    1.36
    Act Density 0.251%

    No Known Activations