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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values and programming syntax

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

    magic angle spinning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.65
     '\\;'
    -0.47
     lokalen
    -0.45
    iastes
    -0.43
    eradish
    -0.42
     afge
    -0.42
     Italij
    -0.42
    WriteBarrier
    -0.41
    曖昧さ回避
    -0.40
    NewUrlParser
    -0.40
    POSITIVE LOGITS
     magic
    1.23
    magic
    1.18
    Magic
    1.14
     magical
    1.11
     Magic
    1.09
    MAGIC
    1.03
     magique
    1.02
     mágica
    1.02
     mágico
    1.00
     MAGIC
    0.97
    Act Density 0.023%

    No Known Activations