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

    Neuronpedia

    INDEX
    Explanations

    references to characters in various contexts, indicating a focus on character development and their interactions

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

    "the" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    plural nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     épaules
    -1.17
     vœux
    -1.14
     bienfaits
    -1.11
     genoux
    -1.02
     dieux
    -1.02
     âmes
    -1.01
     attentes
    -1.00
     bénéfices
    -0.99
     oreilles
    -0.98
     pouvoirs
    -0.97
    POSITIVE LOGITS
     IPs
    0.98
     machines
    0.87
     creations
    0.85
     ones
    0.84
     installations
    0.83
     setups
    0.83
     romances
    0.83
     portfolios
    0.83
     PDFs
    0.82
     complexes
    0.82
    Act Density 0.786%

    No Known Activations