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

    Neuronpedia

    INDEX
    Explanations

    references to tables and data structures

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

    table

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.51
    inSlope
    -0.50
     queſta
    -0.46
    manship
    -0.44
     Autorizaciones
    -0.43
    ParallelGroup
    -0.42
     Avent
    -0.42
    ardust
    -0.42
    versario
    -0.41
     doInBackground
    -0.41
    POSITIVE LOGITS
     table
    2.02
     Table
    1.78
     tables
    1.72
    Table
    1.62
     Tables
    1.58
    table
    1.51
    Tables
    1.35
     TABLE
    1.29
     TABLES
    1.26
    TABLE
    1.21
    Act Density 0.082%

    No Known Activations