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

    Neuronpedia

    INDEX
    Explanations

    terms related to policies and ideological positions in political discourse

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

    policy, strategy, and line

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.40
     reputación
    -0.38
    queryInterface
    -0.36
    middels
    -0.29
     difusión
    -0.29
     rijden
    -0.29
     depresión
    -0.29
     conocimiento
    -0.28
    อย
    -0.27
    countDown
    -0.27
    POSITIVE LOGITS
    évaluateur
    0.65
     strategy
    0.65
    lickr
    0.63
    strategy
    0.63
    ScopeManager
    0.62
     approach
    0.61
     Approach
    0.61
     Anſ
    0.60
    approach
    0.60
    policy
    0.60
    Act Density 0.282%

    No Known Activations