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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to data and its associated attributes or information

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

    associated with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     racist
    -0.42
     الاطلاع
    -0.42
     rusted
    -0.40
     teflon
    -0.40
    leby
    -0.40
     disposable
    -0.39
     bounded
    -0.38
    acuzzi
    -0.38
     broke
    -0.37
    ContentAsync
    -0.36
    POSITIVE LOGITS
     AssemblyCulture
    0.61
    rungsseite
    0.56
     nakalista
    0.47
    :✨
    0.46
    homonymie
    0.45
    tagHelperRunner
    0.45
     సౌకర్య
    0.44
    出版年
    0.43
    hnout
    0.43
     rodea
    0.43
    Act Density 0.001%

    No Known Activations