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

    Neuronpedia

    INDEX
    Explanations

    the term "new" and its variations in various contexts

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

    new object creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.82
    xase
    -0.77
    ésultats
    -0.73
     propOrder
    -0.73
    Tembelea
    -0.71
    -0.70
    orsese
    -0.69
    setVerticalGroup
    -0.69
    niſſe
    -0.68
    abestanden
    -0.67
    POSITIVE LOGITS
    new
    0.45
     new
    0.38
     New
    0.35
     poly
    0.33
    New
    0.32
    0.32
    agent
    0.32
    proto
    0.32
    9
    0.31
     proto
    0.31
    Act Density 0.005%
    No Known Activations