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

    Neuronpedia

    INDEX
    Explanations

    references to magical concepts and elements

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

    magic and its synonyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StoreMessageInfo
    -0.52
     kasarigan
    -0.51
     domic
    -0.50
    Dort
    -0.49
    Fiche
    -0.47
     entourage
    -0.46
    gemeen
    -0.45
    Criterion
    -0.44
     favourable
    -0.44
     accommod
    -0.43
    POSITIVE LOGITS
     magic
    0.61
     witchcraft
    0.56
     sorcery
    0.56
     magia
    0.55
     magical
    0.55
     magique
    0.54
     mág
    0.49
     mágica
    0.48
     mezzi
    0.48
    magical
    0.47
    Act Density 0.019%

    No Known Activations