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

    Neuronpedia

    INDEX
    Explanations

    closing delimiters and code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    constexpr
    0.55
    ({\
    0.52
    (@"
    0.47
    ^{*}(\
    0.46
    𒇽
    0.45
    ($"{
    0.45
    Delicious
    0.44
    ($"
    0.44
    ÈRE
    0.43
    ([...
    0.43
    POSITIVE LOGITS
     "")
    0.85
     "");
    0.82
     [])
    0.77
     _)
    0.77
     ...)
    0.76
    ...)
    0.75
     )
    0.71
     '')
    0.71
    [])
    0.68
     {})
    0.64
    Act Density 0.313%

    No Known Activations