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

    Neuronpedia

    INDEX
    Explanations

    occurrences of curly brackets in code structures

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

    code elements and programming context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.76
    -0.73
     nawr
    -0.73
    ArrowToggle
    -0.71
     ſche
    -0.70
     kaarangay
    -0.69
     occaf
    -0.69
     InputDecoration
    -0.69
    parsedMessage
    -0.66
    mybatisplus
    -0.66
    POSITIVE LOGITS
     {
    0.61
     Sünde
    0.47
     począ
    0.42
     Cię
    0.40
     confortável
    0.39
     păr
    0.39
    {
    0.39
     kobieta
    0.38
     polskiego
    0.38
    ({
    0.37
    Act Density 0.004%

    No Known Activations