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

    Neuronpedia

    INDEX
    Explanations

    incorporating elements and influences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     explan
    0.39
     deme
    0.38
    LastGenOutput
    0.38
    entor
    0.37
     Character
    0.37
     subsection
    0.36
     ویکی
    0.36
     describ
    0.36
    igenschaft
    0.36
    inguished
    0.35
    POSITIVE LOGITS
     elements
    1.91
     elementos
    1.67
    elements
    1.63
     элементы
    1.63
     éléments
    1.55
     элементов
    1.53
     عناصر
    1.52
    Elements
    1.47
    元素
    1.47
     ELEMENTS
    1.45
    Act Density 0.060%

    No Known Activations