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

    Neuronpedia

    INDEX
    Explanations

    references to a specific political plan or initiative

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

    plan or Mahathir

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.56
    osoba
    -0.54
    titleMargin
    -0.52
     poire
    -0.52
     NSCoder
    -0.51
     noDo
    -0.50
    帖最后由
    -0.50
    expandindo
    -0.49
    GOTREF
    -0.49
    المناصب
    -0.49
    POSITIVE LOGITS
     plan
    0.81
    plan
    0.70
     Plan
    0.67
    Plan
    0.64
     plans
    0.63
     PLAN
    0.58
     planning
    0.55
    Plans
    0.55
     Plans
    0.54
     계획
    0.50
    Act Density 0.008%

    No Known Activations