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

    Neuronpedia

    INDEX
    Explanations

    structured data formats or syntax elements, typically used in programming or markup languages

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

    opening curly braces {

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.55
    évaluateur
    -0.54
    SBATCH
    -0.54
    estacks
    -0.53
    ViewImports
    -0.51
    IBOutlet
    -0.48
    autoreleasepool
    -0.48
    GEBURTSDATUM
    -0.47
     stället
    -0.47
    Personensuche
    -0.46
    POSITIVE LOGITS
    },{
    1.55
    ',{
    1.54
    ",{
    1.52
    ,{
    1.41
    ":{
    0.99
    :{
    0.85
    ':{
    0.83
    +{
    0.78
    }:{
    0.72
    }-{
    0.70
    Act Density 0.008%

    No Known Activations