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

    Neuronpedia

    INDEX
    Explanations

    words related to positivity and positive concepts

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

    positive outlook, identification, action, values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gbarkeit
    -0.47
    WebServlet
    -0.45
    AccessFile
    -0.44
     lucky
    -0.43
     vœ
    -0.42
     gouver
    -0.42
     Consultez
    -0.41
    popularity
    -0.41
     ainfi
    -0.40
     coucher
    -0.40
    POSITIVE LOGITS
     reinforcement
    0.57
     vibes
    0.50
     estekak
    0.48
     momentum
    0.47
     thinking
    0.46
     impact
    0.45
     influence
    0.44
     outlook
    0.44
     affirmation
    0.44
    extAlignment
    0.44
    Act Density 0.020%

    No Known Activations