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

    Neuronpedia

    INDEX
    Explanations

    formatted string outputs in code, particularly those involving variable names and types

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

    Formatting/code with brackets and commas

    np_acts-logits-general · gemini-2.0-flash

    code formatting with commas and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "
    -0.78
     «
    -0.64
     “
    -0.61
    「
    -0.56
     '
    -0.54
    mainAxisSize
    -0.50
     ''
    -0.49
    leh
    -0.46
     „
    -0.45
    :@"
    -0.40
    POSITIVE LOGITS
     متعلقه
    1.13
    Geplaatst
    1.08
    الإنجليزية
    1.08
    Personendaten
    1.06
     AssemblyCompany
    1.05
     Савезне
    1.05
     snippetHide
    1.04
    تقاوى
    1.02
    ]")]
    1.02
     ویکی‌پدی
    1.01
    Act Density 0.061%

    No Known Activations