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

    Neuronpedia

    INDEX
    Explanations

    terms related to political organizations and their influences

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

    policy think tanks and institutes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     argint
    -0.35
     pourriez
    -0.33
     universelle
    -0.33
     médicale
    -0.33
     AnyObject
    -0.32
     dentaire
    -0.32
     zru
    -0.32
     prodej
    -0.32
    บาล
    -0.31
    seller
    -0.30
    POSITIVE LOGITS
     think
    1.11
    think
    0.94
     policy
    0.93
     Think
    0.93
     Policy
    0.92
    Think
    0.89
     Brookings
    0.87
    Policy
    0.83
    policy
    0.82
    THINK
    0.79
    Act Density 0.091%

    No Known Activations