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

    Neuronpedia

    INDEX
    Explanations

    JSON structure and organization

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

    Code containing curly brackets and colons

    np_acts-logits-general · gemini-2.0-flash

    `:` `{` `}` `[` `]` `{` `}`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endphp
    -0.73
    archiviato
    -0.54
    期刊论文
    -0.53
     NSMutable
    -0.52
    -0.50
    setViewName
    -0.47
    rstrip
    -0.47
    HasAnnotation
    -0.47
    ابت
    -0.46
    getRuntime
    -0.46
    POSITIVE LOGITS
     {
    1.25
    {
    1.09
    \{
    0.84
     {
    0.83
    ])){
    0.76
    {
    0.75
    ｛
    0.74
    '])){
    0.73
     \{
    0.71
     {@
    0.71
    Act Density 0.373%

    No Known Activations