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

    Neuronpedia

    INDEX
    Explanations

    phrases related to relationships and interactions between subjects or entities

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

    Followed by determinants of the form "of a" or "of the"

    np_acts-logits-general · gemini-2.0-flash

    foreign language words and math/code terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     McG
    -0.48
     Eastern
    -0.47
    </em>
    -0.45
     dotenv
    -0.44
    eam
    -0.44
    gh
    -0.43
    麻
    -0.43
     Western
    -0.43
     dramatic
    -0.42
     Chief
    -0.42
    POSITIVE LOGITS
     propOrder
    0.88
     quelcon
    0.88
     termica
    0.86
     naturais
    0.78
     térm
    0.76
     pulmonar
    0.75
     ainfi
    0.73
     colère
    0.72
     scolaires
    0.72
     financeira
    0.72
    Act Density 2.035%

    No Known Activations