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

    Neuronpedia

    INDEX
    Explanations

    structured data formats, specifically key-value pairs in arrays and objects

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

    code/data structure delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     auroit
    -0.52
    tagHelperRunner
    -0.51
     Bewußt
    -0.47
     arşivlendi
    -0.45
    bentar
    -0.44
    EndContext
    -0.44
     Öffnen
    -0.43
     maș
    -0.43
    DoubleQuotes
    -0.43
     Einfluß
    -0.42
    POSITIVE LOGITS
    ']['
    2.36
    "]["
    2.25
    ')['
    0.99
    `.`
    0.96
    ':{'
    0.93
    ":{"
    0.91
    ]['
    0.88
    ]["
    0.85
    '][$
    0.80
    )['
    0.75
    Act Density 0.009%

    No Known Activations