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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of being "good" or having positive qualities

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

    good followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Życiorys
    -0.45
     utafitiHapana
    -0.43
    hilation
    -0.42
    🇶
    -0.42
    Enllaces
    -0.42
     termica
    -0.42
    contentLoaded
    -0.41
    importanza
    -0.41
     recogida
    -0.41
    IContainer
    -0.39
    POSITIVE LOGITS
    BufferException
    0.66
    GIVEREF
    0.45
     bicchiere
    0.44
    BagLayout
    0.43
    HomeAsUpEnabled
    0.41
     paio
    0.40
     vod
    0.39
     favori
    0.38
     يتيمه
    0.38
     vuitton
    0.38
    Act Density 0.059%

    No Known Activations