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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and specific format structures in documents

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

    mathematical alignment symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.67
     ControllerBase
    -0.62
    ItemBackground
    -0.61
    Sklici
    -0.59
    WriteTagHelper
    -0.59
     betweenstory
    -0.59
    RegressionTest
    -0.57
    AsUp
    -0.57
    Ӕ
    -0.57
    webElementXpaths
    -0.56
    POSITIVE LOGITS
     also
    0.38
    unts
    0.36
     twister
    0.34
    까
    0.34
    %;">
    0.34
     clue
    0.34
     ferma
    0.34
     wiederum
    0.34
     blackout
    0.34
     Morm
    0.33
    Act Density 0.009%

    No Known Activations