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

    Neuronpedia

    INDEX
    Explanations

    Excerpts from various sources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     detalle
    -0.08
     velha
    -0.08
     detalhe
    -0.08
    _DETAIL
    -0.08
     توسط
    -0.07
     효
    -0.07
     детал
    -0.07
     detay
    -0.07
     endings
    -0.07
    ницы
    -0.07
    POSITIVE LOGITS
    认为
    0.19
     believe
    0.15
     believes
    0.14
     believed
    0.14
    ，据
    0.13
     કહે
    0.13
     લાગે
    0.13
    عتقد
    0.12
     argued
    0.12
     মনে
    0.12
    Act Density 0.201%

    No Known Activations