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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting in text

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

    Code snippets or code-related text

    np_acts-logits-general · gemini-2.0-flash

    mathematical alignment and research participation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Portale
    -0.69
    SourceChecksum
    -0.63
    <eos>
    -0.54
     bas
    -0.51
    المراجع
    -0.46
     Finney
    -0.45
    Einzelnachweise
    -0.44
    Jong
    -0.43
    tsburgh
    -0.43
    بود
    -0.42
    POSITIVE LOGITS
    IntoConstraints
    0.88
    AccessorTable
    0.65
    \}\\
    0.58
    DoubleQuotes
    0.58
     referenties
    0.57
    ArgsConstructor
    0.56
    XtraBars
    0.55
     الحره
    0.54
    Toy
    0.54
     UIAlert
    0.54
    Act Density 0.035%

    No Known Activations