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

    Neuronpedia

    INDEX
    Explanations

    highly significant numerical values associated with properties or identifiers

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

    comments and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uxxxx
    -1.02
    niſſe
    -0.95
    IntoConstraints
    -0.95
    Hentet
    -0.92
     esternos
    -0.92
    httphttps
    -0.92
    aarrggbb
    -0.91
    <unused14>
    -0.90
    tagHelperRunner
    -0.89
    SharedDtor
    -0.89
    POSITIVE LOGITS
     \\
    0.37
    (
    0.30
    /
    0.30
     (
    0.29
    class
    0.28
    -
    0.28
     
    0.27
    ↵
    0.27
     /
    0.27
    :
    0.27
    Act Density 0.021%

    No Known Activations