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

    Neuronpedia

    INDEX
    Explanations

    code syntax elements and structure in programming languages

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

    Code snippets or code-related syntax

    np_acts-logits-general · gemini-2.0-flash

    code closing delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.87
     pleaſure
    -0.87
     myſelf
    -0.86
     Jefus
    -0.86
    neſs
    -0.86
     ་་
    -0.84
     ſtate
    -0.84
     faſt
    -0.83
     ſind
    -0.82
    ^(@)
    -0.82
    POSITIVE LOGITS
    ↵↵
    0.66
    <eos>
    0.66
    ↵
    0.64
    </i>
    0.63
    <unused63>
    0.63
    </blockquote>
    0.60
    <unused61>
    0.58
    <unused60>
    0.58
    </code>
    0.55
    ↵↵↵
    0.55
    Act Density 0.943%

    No Known Activations