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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and syntax related to functions and structure in code

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

    Code block beginnings

    np_acts-logits-general · gemini-2.0-flash

    programming begin/end blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumi
    -0.89
     contextLoads
    -0.85
     $_"
    -0.74
    enumii
    -0.73
    }$​
    -0.73
    -0.73
    >\<^
    -0.72
    kuuta
    -0.72
    $")
    -0.71
    ^(@)
    -0.71
    POSITIVE LOGITS
     let
    0.69
     begin
    0.68
    if
    0.67
    begin
    0.62
     do
    0.62
    local
    0.61
     if
    0.61
    let
    0.59
     end
    0.59
    setof
    0.58
    Act Density 0.881%

    No Known Activations