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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and data structure definitions

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

    programming constants and system errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    webElementXpaths
    -0.57
     pleaſure
    -0.54
     ſta
    -0.54
    AndEndTag
    -0.50
     تضيفلها
    -0.49
     cæ
    -0.48
    ſelf
    -0.48
     houſe
    -0.46
     faſt
    -0.44
     pleaf
    -0.44
    POSITIVE LOGITS
     Schiffe
    0.46
     Comunicación
    0.41
     notamment
    0.41
     Савезне
    0.41
     Behör
    0.41
     mierda
    0.41
     Asamblea
    0.40
     asamblea
    0.39
     Soares
    0.39
    المشاركات
    0.39
    Act Density 0.188%

    No Known Activations