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

    Neuronpedia

    INDEX
    Explanations

    scientific paper sections, beginning of abstracts, and the start of new sections in HTML or markdown files.

    oai_token-act-pair · gemini-2.0-flash

    Scientific text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    makeConstraints
    -0.63
    abestanden
    -0.62
     propOrder
    -0.54
    зулта
    -0.50
     Biôgrafia
    -0.50
     nakalista
    -0.49
    <_>
    -0.49
    =?,
    -0.48
     Charlemagne
    -0.48
    Vorlage
    -0.48
    POSITIVE LOGITS
    ukone
    0.59
    ScopeManager
    0.58
    richTextPanel
    0.57
    بوابة
    0.56
     IBOutlet
    0.54
    principalTable
    0.53
    Glob
    0.52
    клопе
    0.52
    PickerController
    0.52
     reutiliz
    0.51
    Act Density 4.399%

    No Known Activations