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

    Neuronpedia

    INDEX
    Explanations

    intelligence and cleverness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ন
    1.45
    et
    1.25
    j
    1.25
     khảo
    1.17
    weds
    1.16
    ॅमिली
    1.16
    াইভ
    1.15
    ান
    1.13
     aliments
    1.13
     humides
    1.13
    POSITIVE LOGITS
    な
    1.27
    ية
    1.20
    ता
    1.18
    はなく
    1.14
     соблю
    1.13
    Wise
    1.09
     lógica
    1.09
    이고
    1.08
     consape
    1.08
    이라는
    1.06
    Act Density 0.476%

    No Known Activations