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

    Neuronpedia

    INDEX
    Explanations

    references to tables in the text

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

    table references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BDS
    -0.43
    peda
    -0.41
     Aussie
    -0.41
     koala
    -0.41
     insiders
    -0.40
    himo
    -0.40
     ODS
    -0.39
    demik
    -0.39
    GHS
    -0.39
     RSI
    -0.39
    POSITIVE LOGITS
     Table
    3.16
    Table
    2.61
     TABLE
    2.09
     table
    2.08
     Tables
    2.02
     tables
    1.65
    TABLE
    1.63
    Tables
    1.62
    getTable
    1.51
     TABLES
    1.49
    Act Density 0.016%

    No Known Activations