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

    Neuronpedia

    INDEX
    Explanations

    references to figures and data visualizations in the text

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

    citation figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.77
    httphttps
    -0.69
    fjspx
    -0.58
     चीज़ों
    -0.56
    bootstrapcdn
    -0.55
    ReusableCell
    -0.55
     صوتيه
    -0.52
    qrstuvwxyz
    -0.51
     wikipagina
    -0.51
    المشاركات
    -0.50
    POSITIVE LOGITS
     guste
    0.40
     faisons
    0.38
    DataGrid
    0.36
    >//
    0.35
     по
    0.34
    ).
    0.34
    ViewFeatures
    0.34
    Obrázky
    0.33
     Thornton
    0.33
     although
    0.33
    Act Density 0.322%

    No Known Activations