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

    Neuronpedia

    INDEX
    Explanations

    references to magic or magical themes

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

    magic and magician

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AsUp
    -0.90
    findpost
    -0.83
    ########.
    -0.81
     HasFactory
    -0.79
    <unused28>
    -0.74
    <pad>
    -0.74
    <unused14>
    -0.73
    <unused41>
    -0.73
    <unused8>
    -0.73
    <unused3>
    -0.73
    POSITIVE LOGITS
     magic
    0.95
    magic
    0.84
     mágica
    0.82
     magia
    0.82
     magique
    0.81
     mágico
    0.79
     magical
    0.78
     MAGIC
    0.75
     magician
    0.75
    MAGIC
    0.73
    Act Density 0.130%

    No Known Activations