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

    Neuronpedia

    INDEX
    Explanations

    references to political ideologies and their outcomes

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

    Comparison or superlative adjectives

    np_acts-logits-general · gemini-2.0-flash

    clear victor or better

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     >=",
    -0.73
    RectangleBorder
    -0.67
    KURZBESCHREIBUNG
    -0.66
     another
    -0.65
    another
    -0.63
    "])
    -0.60
     Another
    -0.60
    Économie
    -0.57
    Another
    -0.57
     endforeach
    -0.56
    POSITIVE LOGITS
     dominant
    1.29
     predominate
    1.15
     dominance
    1.09
     dominates
    1.08
    dominant
    1.08
     dominate
    1.04
     Dominant
    1.04
     predominant
    1.03
     predominance
    1.02
     dominante
    1.02
    Act Density 0.562%

    No Known Activations