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

    Neuronpedia

    INDEX
    Explanations

    This is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Основ
    0.51
    вшейся
    0.45
     رسول
    0.44
    ковое
    0.44
     stvarn
    0.42
    liği
    0.40
    луйста
    0.40
    اليه
    0.40
     정말
    0.40
    是我
    0.39
    POSITIVE LOGITS
     including
    0.57
     incluindo
    0.55
     einschließlich
    0.52
    including
    0.50
     include
    0.47
     consisting
    0.47
     включая
    0.45
     includes
    0.45
     incluyen
    0.45
     incluem
    0.44
    Act Density 0.153%

    No Known Activations