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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology, machines, and instructional content

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

    appearing before nouns

    np_acts-logits-general · gemini-2.0-flash

    lists of systems and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     épaules
    -0.99
     lèvres
    -0.95
     âmes
    -0.84
     oreilles
    -0.84
     genoux
    -0.80
     vœux
    -0.78
     dieux
    -0.77
     Grecs
    -0.76
     bienfaits
    -0.74
     preuves
    -0.73
    POSITIVE LOGITS
     processes
    1.02
     technologies
    1.00
     procedures
    0.93
     structures
    0.91
     behaviors
    0.88
     programs
    0.87
     philosophies
    0.86
     behaviours
    0.85
     techniques
    0.85
     cultures
    0.84
    Act Density 0.357%

    No Known Activations