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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the quality of various services or products

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

    quality of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تعدى
    -0.46
     Navidad
    -0.36
     Bisnis
    -0.34
     Penrose
    -0.32
     Consultez
    -0.32
     Justo
    -0.32
    avocat
    -0.31
     siège
    -0.31
     inauguración
    -0.31
    ientôt
    -0.31
    POSITIVE LOGITS
     quality
    1.00
    quality
    0.95
    Quality
    0.87
     Quality
    0.82
     QUALITY
    0.80
    QUALITY
    0.76
     qualidade
    0.74
     Qualität
    0.73
     качество
    0.73
     kwaliteit
    0.72
    Act Density 0.007%

    No Known Activations