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

    Neuronpedia

    INDEX
    Explanations

    punctuation and numerical markers in the text

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

    section results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    complexContent
    -0.79
    AddTagHelper
    -0.78
     propOrder
    -0.78
     CreateTagHelper
    -0.78
     defaultstate
    -0.74
    bkz
    -0.72
    StoreMessageInfo
    -0.72
    setVerticalGroup
    -0.71
     ویکی‌پدی
    -0.69
    RenderAtEndOf
    -0.67
    POSITIVE LOGITS
    /
    0.36
    Incoming
    0.35
     Fort
    0.34
     Studio
    0.33
     Bacon
    0.32
     "
    0.32
     Bab
    0.32
    körper
    0.31
     Lips
    0.31
     Menu
    0.31
    Act Density 0.000%

    No Known Activations