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

    Neuronpedia

    INDEX
    Explanations

    instances of common pronouns and articles within the text

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

    baby cards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.77
    ValueGeneration
    -0.56
    MigrationBuilder
    -0.55
    Aholisi
    -0.53
     Regierungs
    -0.53
     dezelve
    -0.53
    ennemi
    -0.53
     negativas
    -0.52
     zoude
    -0.52
     ProtoMessage
    -0.51
    POSITIVE LOGITS
     styl
    0.45
     visually
    0.45
     artwork
    0.44
     sopra
    0.40
     stylish
    0.40
     visuals
    0.39
     pict
    0.39
    setColor
    0.38
     products
    0.37
     seal
    0.37
    Act Density 0.035%

    No Known Activations