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

    Neuronpedia

    INDEX
    Explanations

    ways to access or describe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Shoes
    0.48
    vä
    0.48
     Спа
    0.46
    Есть
    0.46
     Вам
    0.46
    ším
    0.45
    Спа
    0.44
    ﺴ
    0.44
     Shoe
    0.43
     gelangen
    0.43
    POSITIVE LOGITS
     prudence
    0.46
     ಅಗ
    0.44
    ifies
    0.44
     logical
    0.42
    <unused85>
    0.41
    으면
    0.41
     કોઈપણ
    0.41
    <unused83>
    0.40
    ICATION
    0.40
     সমস্ত
    0.40
    Act Density 0.002%

    No Known Activations