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

    Neuronpedia

    INDEX
    Explanations

    a standard format for citations with multiple authors.

    oai_token-act-pair · gemini-2.0-flash

    Physics publications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TestingModule
    -0.65
    complexContent
    -0.63
     ghế
    -0.52
     kurzer
    -0.50
    ocz
    -0.49
    سكري
    -0.49
     linguistique
    -0.49
    gridx
    -0.48
     Pulitzer
    -0.46
     reutiliz
    -0.46
    POSITIVE LOGITS
    참고
    0.59
    مقاله
    0.57
    ++
    0.57
    談社
    0.54
    '}>
    0.53
    ')}}"
    0.52
     تضيفلها
    0.51
    ']]
    0.51
    WriteTagHelper
    0.49
    ')['
    0.49
    Act Density 2.641%

    No Known Activations