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

    Neuronpedia

    INDEX
    Explanations

    references to tables

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

    tables and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noDo
    -0.47
     Bestand
    -0.43
     تضيفلها
    -0.41
    rophilic
    -0.40
     Comando
    -0.40
     Schall
    -0.39
    Дж
    -0.39
    cillors
    -0.37
    symptoms
    -0.37
    Inhoud
    -0.36
    POSITIVE LOGITS
     tables
    2.56
    Tables
    2.42
     Tables
    2.36
     TABLES
    2.23
    tables
    2.22
    TABLES
    1.89
     Tabellen
    1.20
     tablas
    1.16
     table
    1.13
    テーブル
    1.00
    Act Density 0.005%

    No Known Activations