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

    Neuronpedia

    INDEX
    Explanations

    code structure including braces and function definitions

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

    LaTeX math mode expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols and code punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蚪
    -0.46
     للاسماء
    -0.44
     للمعارف
    -0.44
    Rhestr
    -0.41
    hnia
    -0.41
    ลำ
    -0.41
     refer
    -0.41
    filepath
    -0.40
    BeginInit
    -0.40
     navideñas
    -0.39
    POSITIVE LOGITS
     //$
    0.53
     daß
    0.50
     \,
    0.47
     !?
    0.47
     }{@
    0.45
     defStyle
    0.45
    ]--;
    0.42
    tagHelperRunner
    0.42
     /
    0.41
     ๆ
    0.41
    Act Density 0.571%

    No Known Activations