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

    Neuronpedia

    INDEX
    Explanations

    references to sensitive or classified information related to investigations

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

    Russia investigation and Page

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endpush
    -0.40
    seamnă
    -0.39
    /*---
    -0.36
     dalamnya
    -0.35
    Ārējās
    -0.33
    MergeFrom
    -0.33
    entador
    -0.33
    Cyfarwyddwr
    -0.32
    omitempty
    -0.31
    orska
    -0.31
    POSITIVE LOGITS
    0.50
     للاسماء
    0.47
    Labor
    0.47
    ruik
    0.47
     śmier
    0.47
     Putih
    0.44
     الرياضيه
    0.43
     Hez
    0.42
    Watts
    0.42
    Emails
    0.41
    Act Density 0.212%

    No Known Activations