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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting markers

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

    identifying personal information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الإنجليزية
    -0.66
    uxxxx
    -0.64
    ագրություններ
    -0.64
    tinyos
    -0.63
    Tikang
    -0.62
    tagHelperRunner
    -0.60
    出版年
    -0.60
     يتيمه
    -0.55
    Зноскі
    -0.54
     ویکی‌پدی
    -0.52
    POSITIVE LOGITS
    ...
    0.47
    Personendaten
    0.42
    L
    0.40
    …
    0.39
    3
    0.38
    lly
    0.36
    PS
    0.36
     S
    0.36
    abar
    0.35
    l
    0.35
    Act Density 0.001%

    No Known Activations