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

    Neuronpedia

    INDEX
    Explanations

    occurrences and frequency of numbers and statistical data in the text

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

    double blind randomised

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.58
     للمعارف
    -0.57
    principalTable
    -0.52
     ujednoznacz
    -0.52
    alanta
    -0.49
    FunctionFlags
    -0.48
    HtmlAttribute
    -0.46
    tagHelperRunner
    -0.46
     ſont
    -0.46
    protoimpl
    -0.45
    POSITIVE LOGITS
     оригіналу
    0.45
     colspan
    0.43
     outdoor
    0.41
    yn
    0.40
     diamond
    0.39
    Rujuakan
    0.38
     non
    0.38
    ErrMsg
    0.37
     superstar
    0.37
     Urqu
    0.37
    Act Density 0.100%

    No Known Activations