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

    Neuronpedia

    INDEX
    Explanations

    concepts related to legal terms and frameworks

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

    policies and systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    chmal
    -0.39
    una
    -0.37
     Wul
    -0.36
    iação
    -0.35
    ้าว
    -0.35
    hWnd
    -0.35
    leding
    -0.34
     pertenec
    -0.34
    estimable
    -0.34
    Shapes
    -0.33
    POSITIVE LOGITS
     policy
    0.72
     arrangement
    0.68
     ſche
    0.65
     approach
    0.64
     regime
    0.64
     scheme
    0.64
    policy
    0.62
     policies
    0.62
     principle
    0.60
    approach
    0.60
    Act Density 0.107%

    No Known Activations