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

    Neuronpedia

    INDEX
    Explanations

    references to data structures and formatted outputs

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

    Code snippets with brackets and/or parentheses

    np_acts-logits-general · gemini-2.0-flash

    code block end markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.64
     désolés
    -0.57
    [{{
    -0.56
    ([
    -0.53
    ([[
    -0.53
     đương
    -0.53
    ([-
    -0.52
    awtextra
    -0.52
    AlterField
    -0.52
    InvalidProtocol
    -0.49
    POSITIVE LOGITS
     etc
    0.67
    etc
    0.62
     ...,
    0.59
     //
    0.58
    \
    0.56
    ?,?,
    0.55
     ...)
    0.54
    ...,
    0.54
     …)
    0.54
     /*
    0.54
    Act Density 0.175%

    No Known Activations