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

    Neuronpedia

    INDEX
    Explanations

    references, citations, and links to academic articles

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

    Citations with DOIs or URLs followed by a period

    np_acts-logits-general · gemini-2.0-flash

    citations and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    weile
    -0.57
    ()?;
    -0.56
    neté
    -0.54
    četně
    -0.53
     '*':
    -0.53
    டுத்த
    -0.52
     pleaſure
    -0.52
    ();}
    -0.52
    ISTRATION
    -0.52
    ักษ
    -0.51
    POSITIVE LOGITS
    Datuak
    0.64
    .
    0.61
     مشين
    0.58
    TagMode
    0.56
    CodeAttribute
    0.53
     وتسجيلات
    0.53
     sánh
    0.51
    WriteTagHelper
    0.50
    Jîn
    0.49
    허
    0.49
    Act Density 0.076%

    No Known Activations