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

    Neuronpedia

    INDEX
    Explanations

    references to academic authors and citations

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

    academic publications

    np_acts-logits-general · gemini-2.0-flash

    scientific citations journal names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.63
     again
    -0.59
     day
    -0.59
     안
    -0.57
    IndentedString
    -0.56
    GEBURTSDATUM
    -0.54
    안
    -0.54
    ViewFeatures
    -0.54
    gorod
    -0.52
    czuk
    -0.51
    POSITIVE LOGITS
    __':
    0.80
     unpublished
    0.78
     Waray
    0.73
    unpublished
    0.66
    __":
    0.64
    __':
    0.63
    ;">
    0.63
    eradish
    0.62
    ;;)
    0.62
    )_/¯
    0.59
    Act Density 0.180%

    No Known Activations