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

    Neuronpedia

    INDEX
    Explanations

    quotations and punctuation marks in the text

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

    Delimiters: quotes and parentheses

    np_acts-logits-general · gemini-2.0-flash

    string literals and code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ‘
    -0.80
    vastava
    -0.68
    Искәрмәләр
    -0.61
     Mora
    -0.56
     ‚
    -0.54
    chaik
    -0.52
     ’
    -0.52
    anes
    -0.52
     Montal
    -0.51
     './../
    -0.51
    POSITIVE LOGITS
    .'"
    0.77
     ")"
    0.74
     uintptr
    0.71
    |"
    0.71
    MessageTagHelper
    0.70
    apunov
    0.70
    %"
    0.68
    
    0.67
    ">"
    0.66
     "..."
    0.66
    Act Density 0.235%

    No Known Activations