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

    Neuronpedia

    INDEX
    Explanations

    emphasis on inclusivity and attention to details

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

    every instance or aspect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     marge
    -0.35
    BeginInit
    -0.32
     only
    -0.32
    참고
    -0.32
     gratuitement
    -0.32
     múltiple
    -0.31
     bý
    -0.31
    겨
    -0.31
    TintMode
    -0.31
     multiple
    -0.31
    POSITIVE LOGITS
     aspect
    0.94
     detail
    0.79
     facet
    0.77
     aspects
    0.75
    aspect
    0.71
     moment
    0.70
     facets
    0.69
    aspects
    0.66
    detail
    0.65
     ounce
    0.65
    Act Density 0.022%

    No Known Activations