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

    Neuronpedia

    INDEX
    Explanations

    references to character dynamics and relationships in narratives

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

    Adjectives describing a person or thing

    np_acts-logits-general · gemini-2.0-flash

    describes qualities or character

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    esgue
    -0.72
     térmico
    -0.71
     spéciaux
    -0.70
     intérieure
    -0.66
     supérieures
    -0.66
     spéciale
    -0.64
     étrangère
    -0.63
    kijken
    -0.61
    Gambas
    -0.61
    UserScript
    -0.60
    POSITIVE LOGITS
     sleek
    1.15
     elegant
    1.05
     rugged
    1.01
     cheerful
    0.98
     gritty
    0.97
     playful
    0.97
     calm
    0.97
     suave
    0.96
     soft
    0.95
     energetic
    0.95
    Act Density 0.581%

    No Known Activations