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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical comparisons and quantities

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

    respective eras

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ceux
    -0.47
     députés
    -0.46
     témoins
    -0.42
     spectateurs
    -0.41
     polskich
    -0.41
     journalistes
    -0.41
     alliés
    -0.40
     azok
    -0.40
     antaranya
    -0.40
     takimi
    -0.40
    POSITIVE LOGITS
     environments
    0.70
     eras
    0.70
     sets
    0.70
     universes
    0.69
     climates
    0.68
     Environments
    0.66
     religions
    0.66
     reputations
    0.66
     regimes
    0.65
     lists
    0.65
    Act Density 0.291%

    No Known Activations