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

    Neuronpedia

    INDEX
    Explanations

    topological and academic subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     demie
    0.52
    üyük
    0.50
     Лю
    0.50
     дета
    0.49
    Основные
    0.49
     основным
    0.48
    Лю
    0.48
    र्दशी
    0.48
    ковий
    0.48
     основных
    0.47
    POSITIVE LOGITS
    i
    0.54
    to
    0.50
    ier
    0.45
    works
    0.45
     to
    0.44
    ia
    0.44
    spirit
    0.43
    tern
    0.43
    mo
    0.42
    wall
    0.42
    Act Density 0.003%

    No Known Activations