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

    Neuronpedia

    INDEX
    Explanations

    code syntax elements and HTML attributes

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

    HTML and non-English words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .*")]
    -0.50
    췄
    -0.44
    trale
    -0.41
     typelib
    -0.40
    GenerationType
    -0.40
    setArguments
    -0.39
    ########.
    -0.38
     Enkel
    -0.38
     SCRIPT
    -0.38
    SizeMode
    -0.38
    POSITIVE LOGITS
     Roskov
    0.54
     ویکی‌پدی
    0.50
     Italijanski
    0.49
     dafs
    0.48
    OGND
    0.48
    цездатний
    0.47
     nakalista
    0.44
     onCancelled
    0.44
     Eſ
    0.43
     nahilalakip
    0.43
    Act Density 0.003%

    No Known Activations