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

    Neuronpedia

    INDEX
    Explanations

    instructions related to troubleshooting or fixing technical problems

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

    install, uninstall, or debug

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.52
    Архівовано
    -0.43
    VersionUID
    -0.41
    archiviato
    -0.41
     DbSet
    -0.41
    viembre
    -0.40
    Билгалдахарш
    -0.39
    instancetype
    -0.38
    Válasz
    -0.37
    rawDesc
    -0.36
    POSITIVE LOGITS
    Aholisi
    0.49
     try
    0.44
     yourself
    0.43
     <>",
    0.43
    Try
    0.42
     Try
    0.42
    oterapia
    0.41
     debug
    0.40
    veland
    0.40
     Debugging
    0.39
    Act Density 0.028%

    No Known Activations