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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the importance or impact of certain actions or attributes

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

    not only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.47
     تضيفلها
    -0.45
     Phaser
    -0.42
    脚注の使い方
    -0.41
    ✨:
    -0.41
    lwjgl
    -0.41
    fjspx
    -0.40
    CreateMap
    -0.40
    GraphicsUnit
    -0.40
     propOrder
    -0.40
    POSITIVE LOGITS
     selain
    0.63
     besides
    0.62
     Besides
    0.57
    besides
    0.57
    Além
    0.54
     além
    0.54
    Besides
    0.53
     Além
    0.53
     mellett
    0.52
     Además
    0.52
    Act Density 0.086%

    No Known Activations