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

    Neuronpedia

    INDEX
    Explanations

    the presence of blocks or constructs in programming code, particularly curly braces and the keyword "begin."

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

    code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InitVars
    -0.63
    WriteLiteral
    -0.59
    addPreferred
    -0.56
    ulongan
    -0.55
     esternos
    -0.55
     Keaton
    -0.54
    mpagne
    -0.54
    majánló
    -0.52
    shtml
    -0.52
    oredCriteria
    -0.51
    POSITIVE LOGITS
    SequentialGroup
    0.59
     cioè
    0.42
    Gambas
    0.39
    ::{
    0.37
     {
    0.35
     désolés
    0.33
    jsii
    0.32
     NUKAT
    0.32
     drodze
    0.32
    ("/{
    0.31
    Act Density 0.023%

    No Known Activations