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

    Neuronpedia

    INDEX
    Explanations

    instances of code snippets or programming language constructs

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

    code language elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rest
    -0.39
    -
    -0.38
    DoubleQuotes
    -0.37
    \
    -0.36
    -0.36
    ★
    -0.35
    emp
    -0.33
    fi
    -0.32
    -.
    -0.31
    emphasis
    -0.30
    POSITIVE LOGITS
    <code>
    2.11
     setCode
    0.79
     Chwiliwch
    0.79
     getCode
    0.73
     code
    0.69
     CODE
    0.69
     `
    0.68
    CODE
    0.68
     GoogleFonts
    0.67
     '`
    0.66
    Act Density 0.011%

    No Known Activations