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

    Neuronpedia

    INDEX
    Explanations

    occurrences of punctuation or special characters present in text

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

    ’s or s

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تد
    -0.34
    breng
    -0.33
     dec
    -0.33
     informée
    -0.32
     clin
    -0.32
    见
    -0.31
    配
    -0.31
    起
    -0.31
    CodeAttribute
    -0.30
     segre
    -0.30
    POSITIVE LOGITS
    parsedMessage
    0.66
     Wikimedijinoj
    0.66
    webElementXpaths
    0.64
     चीज़ों
    0.61
    RegressionTest
    0.59
     Савезне
    0.59
    揄
    0.57
    DockStyle
    0.56
    enido
    0.56
     GenerationType
    0.56
    Act Density 0.007%

    No Known Activations