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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "policy" in different contexts

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

    policy and decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.52
    AndEndTag
    -0.49
    jsonwebtoken
    -0.48
    expandindo
    -0.48
     становника
    -0.46
     rodríguez
    -0.45
    UserScript
    -0.45
     pinggang
    -0.44
    NameInMap
    -0.44
     barras
    -0.44
    POSITIVE LOGITS
     policy
    0.70
     policies
    0.69
    policy
    0.63
     direction
    0.63
     aimed
    0.61
     decisions
    0.60
    方針
    0.60
     POLICY
    0.59
     Policies
    0.58
     favoring
    0.57
    Act Density 0.033%

    No Known Activations