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

    Neuronpedia

    INDEX
    Explanations

    entire systems or parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     einem
    0.46
     небольшой
    0.44
     недалеко
    0.44
     современной
    0.42
     unui
    0.40
    ispielsweise
    0.40
    semantic
    0.40
    verticalLayout
    0.38
     비슷한
    0.38
     Möglichkeiten
    0.38
    POSITIVE LOGITS
     모든
    0.62
     entire
    0.59
    全ての
    0.58
     parts
    0.55
     всех
    0.55
    所有的
    0.55
     equipment
    0.55
     both
    0.54
     products
    0.53
     operations
    0.53
    Act Density 0.229%

    No Known Activations