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

    Neuronpedia

    INDEX
    Explanations

    references, citations, and external documents in a scientific context

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

    References with numbers (e.g., @CR8, @bib48)

    np_acts-logits-general · gemini-2.0-flash

    citations or references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Seven
    -0.73
    Seven
    -0.69
     Seventeen
    -0.68
    7
    -0.67
    seven
    -0.63
     Seventh
    -0.61
     seven
    -0.60
    Seventh
    -0.59
    VII
    -0.59
    july
    -0.58
    POSITIVE LOGITS
    IndentedString
    0.82
    ⑧
    0.77
     AssemblyCulture
    0.76
    ThroughAttribute
    0.72
     tartalomajánló
    0.70
    GEBURTSDATUM
    0.70
     eighth
    0.69
     viii
    0.67
    adaptiveStyles
    0.64
    RegressionTest
    0.64
    Act Density 0.420%

    No Known Activations