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

    Neuronpedia

    INDEX
    Explanations

    phrases related to authors and their contributions in literature

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

    achievements and successful creations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    сылкі
    -0.52
    verifyException
    -0.51
     Wikispecies
    -0.48
     térm
    -0.48
     Jefus
    -0.48
     Roskov
    -0.48
    httphttps
    -0.48
    msgTypes
    -0.46
    ArgumentParser
    -0.45
    :✨
    -0.45
    POSITIVE LOGITS
     succeed
    0.48
     succeeds
    0.47
     succeeded
    0.41
    厥
    0.40
     masterpiece
    0.40
    Зноскі
    0.38
     gelungen
    0.38
     уда
    0.38
    <?>>
    0.37
    ückt
    0.37
    Act Density 0.101%

    No Known Activations