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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe various representations or depictions of concepts and scenarios

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

    depicting a situation or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     curiosidad
    -0.38
     Comprometido
    -0.38
    Izvori
    -0.37
    botines
    -0.35
    ustimmung
    -0.35
     administrativo
    -0.35
    autorisation
    -0.35
     schla
    -0.35
    Conseils
    -0.35
     literario
    -0.34
    POSITIVE LOGITS
     portraying
    0.75
     picture
    0.75
     beeld
    0.72
     portrayal
    0.69
     Picture
    0.68
     portrayed
    0.68
    picture
    0.68
     portray
    0.68
     portrays
    0.68
    ImageContext
    0.67
    Act Density 0.027%

    No Known Activations