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

    Neuronpedia

    INDEX
    Explanations

    occurrences of structured code blocks, particularly in programming languages

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

    Code snippets ending with curly brackets

    np_acts-logits-general · gemini-2.0-flash

    javascript code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "){
    -0.74
     ModelExpression
    -0.72
    ()){
    -0.70
    "){
    -0.69
    '):
    -0.68
    Hozzáférés
    -0.67
    "));
    -0.65
     {}\
    -0.64
    "):
    -0.64
    '])->
    -0.64
    POSITIVE LOGITS
    };
    0.61
    NUMX
    0.52
     aidant
    0.50
     puol
    0.47
     ferru
    0.45
     aveug
    0.45
     Siles
    0.45
     concetto
    0.44
     PFA
    0.43
     PDI
    0.43
    Act Density 0.041%

    No Known Activations