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

    Neuronpedia

    INDEX
    Explanations

    references to magic, magical elements, and supernatural themes

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

    "magic."

    np_acts-logits-general · gemini-2.0-flash

    magic or magical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.85
    principalColumn
    -0.72
    Geplaatst
    -0.66
     dataSnapshot
    -0.66
    ChildScrollView
    -0.65
     ddelweddau
    -0.64
     للاسماء
    -0.63
     utafitiHapana
    -0.62
    TagMode
    -0.62
    ArrowToggle
    -0.62
    POSITIVE LOGITS
     magic
    1.18
     Magic
    1.11
     MAGIC
    1.03
     magia
    1.00
    Magic
    0.99
     magical
    0.98
    MAGIC
    0.98
    magic
    0.97
    magical
    0.94
    Spells
    0.92
    Act Density 0.238%

    No Known Activations