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

    Neuronpedia

    INDEX
    Explanations

    phrases related to learning and acquiring knowledge

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

    learn about or learn how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.78
     gethan
    -0.72
     oprot
    -0.65
     laſſen
    -0.65
     dieſem
    -0.64
     Waſſer
    -0.64
     ſehr
    -0.63
     stiefe
    -0.62
     kasarigan
    -0.62
     ſelbſt
    -0.62
    POSITIVE LOGITS
     learn
    0.91
    Learn
    0.87
     LEARN
    0.83
     Learn
    0.80
    learn
    0.75
     learns
    0.71
     learned
    0.69
     learning
    0.68
    LEARN
    0.68
     Learning
    0.65
    Act Density 0.021%

    No Known Activations