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

    Neuronpedia

    INDEX
    Explanations

    punctuation and braces used in code structures

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

    code snippets and programming keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    styleType
    -0.75
     surla
    -0.71
    -0.67
     NSCoder
    -0.65
     ब्रेकडाउन
    -0.62
    ConstraintMaker
    -0.60
    TryDecodeAsNil
    -0.59
    Cyfarwyddwr
    -0.58
    Aholisi
    -0.58
     typelib
    -0.57
    POSITIVE LOGITS
    ↵
    0.28
     /*
    0.27
     damit
    0.27
    })}$
    0.26
    int
    0.26
     asas
    0.26
     method
    0.26
     //
    0.26
     서
    0.26
    <h1>
    0.25
    Act Density 0.021%

    No Known Activations