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

    Neuronpedia

    INDEX
    Explanations

    code constructs and function definitions related to programming concepts

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

    Code snippets including keywords like "local", "function", and "return"

    np_acts-logits-general · gemini-2.0-flash

    code structure and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Majefty
    -0.88
    ientras
    -0.86
    ^(@)
    -0.85
     Efq
    -0.84
    berdayakan
    -0.83
     $_"
    -0.82
    ſelves
    -0.81
    ſelf
    -0.81
     itſelf
    -0.79
    neſs
    -0.78
    POSITIVE LOGITS
    <eos>
    0.92
    </em>
    0.80
    </code>
    0.71
    ↵↵
    0.70
    ↵↵↵↵
    0.69
     ...
    0.69
    ↵
    0.68
    ↵↵↵
    0.65
    </blockquote>
    0.64
    ()
    0.61
    Act Density 0.343%

    No Known Activations