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

    Neuronpedia

    INDEX
    Explanations

    citations and references in the text

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

    Punctuation, especially parentheses

    np_acts-logits-general · gemini-2.0-flash

    before punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Geplaatst
    -1.08
     AssemblyCompany
    -1.04
    المناصب
    -0.96
     Audiodateien
    -0.94
    RetentionPolicy
    -0.92
    "],
    -0.91
     Савезне
    -0.89
    ^(@)
    -0.85
    __':
    -0.85
    -0.84
    POSITIVE LOGITS
    ↵
    0.73
    ↵↵
    0.62
    <eos>
    0.62
    <code>
    0.58
    CS
    0.53
    ↵↵↵
    0.51
    Check
    0.46
     উ
    0.45
     –
    0.45
     .
    0.43
    Act Density 0.114%

    No Known Activations