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

    Neuronpedia

    INDEX
    Explanations

    mentions of characters or entities in narratives

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

    Dialogue or narration in stories

    np_acts-logits-general · gemini-2.0-flash

    cute, adorable, and adventurous stories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.71
    EndContext
    -0.63
    fuge
    -0.54
     Wraith
    -0.52
     crudo
    -0.50
    ölker
    -0.48
    OwnProperty
    -0.48
     layui
    -0.48
     fucker
    -0.47
     herida
    -0.47
    POSITIVE LOGITS
     adventures
    0.79
     cute
    0.77
     cartoon
    0.73
     adorable
    0.72
     lovable
    0.71
     anthrop
    0.69
     Adventures
    0.68
     mischievous
    0.68
     adventure
    0.68
     mischief
    0.65
    Act Density 0.376%

    No Known Activations