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

    Neuronpedia

    INDEX
    Explanations

    discussions about competency and capability, particularly in relation to gender equality and professional merit

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

    Magic, quests, superpowers and missions

    np_acts-logits-general · gemini-2.0-flash

    magic, superpowers, missions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DeleteBehavior
    -0.72
     ModelExpression
    -0.56
    Lähteet
    -0.54
    harusnya
    -0.53
    parsedMessage
    -0.52
     geslacht
    -0.51
    ChildScrollView
    -0.51
    MessageOf
    -0.49
     picioare
    -0.49
     commento
    -0.48
    POSITIVE LOGITS
     magical
    0.79
     missions
    0.77
     magic
    0.75
     supernatural
    0.73
     superpowers
    0.73
     powers
    0.66
     pacif
    0.64
    magical
    0.64
     mages
    0.63
     bounties
    0.63
    Act Density 0.526%

    No Known Activations