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

    Neuronpedia

    INDEX
    Explanations

    technical terms and expressions related to scientific research and methodologies

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

    End of sentences

    np_acts-logits-general · gemini-2.0-flash

    would be beneficial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.69
    hyrchwyd
    -0.66
     Italijanski
    -0.57
     "..\..\..\
    -0.52
     relâche
    -0.51
     Italijani
    -0.50
    >{@
    -0.49
    Kariera
    -0.46
    Билгалдахарш
    -0.46
    Derbyniad
    -0.46
    POSITIVE LOGITS
     pungkas
    0.58
     aarde
    0.47
    StandardCharsets
    0.46
     pungkasnya
    0.46
    dotte
    0.43
    endpush
    0.41
     enfans
    0.40
    IndentedString
    0.40
     auguri
    0.40
     publicitaires
    0.39
    Act Density 0.208%

    No Known Activations