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

    Neuronpedia

    INDEX
    Explanations

    references to methods or functions in coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Clarinet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.52
    تقاوى
    -0.49
    -0.45
     незавершена
    -0.43
    Ƚ
    -0.42
     ویکی‌پدی
    -0.42
     ujednoznacz
    -0.42
    AnchorTagHelper
    -0.42
    twimg
    -0.42
    apimachinery
    -0.41
    POSITIVE LOGITS
     Administrativna
    0.54
     Collar
    0.49
     collar
    0.47
    damit
    0.47
     computers
    0.47
    collar
    0.45
    jama
    0.45
     Bill
    0.45
     clarinet
    0.44
     flies
    0.44
    Act Density 0.001%

    No Known Activations