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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically periods

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

    common code includes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    -0.40
     Clique
    -0.38
     interp
    -0.37
    9
    -0.36
    8
    -0.36
    user
    -0.33
    4
    -0.32
    6
    -0.32
    yle
    -0.31
    5
    -0.31
    POSITIVE LOGITS
     autorytatywna
    1.00
     CreateTagHelper
    0.92
    aarrggbb
    0.90
    RenderAtEndOf
    0.86
    出版年
    0.82
    évaluateur
    0.81
     betweenstory
    0.78
    hyrchwyd
    0.75
    دانشنامهٔ
    0.75
    OGND
    0.73
    Act Density 0.002%

    No Known Activations