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

    Neuronpedia

    INDEX
    Explanations

    references to personal or local experiences

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

    real time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nodoc
    -0.41
    ++++++++++++++++
    -0.41
    uggles
    -0.35
    ****************
    -0.35
    IBarButtonItem
    -0.34
     Vin
    -0.33
    avaş
    -0.33
     Guy
    -0.32
     Computers
    -0.32
     otomatig
    -0.32
    POSITIVE LOGITS
    TestingModule
    0.72
    Personensuche
    0.69
    LookAnd
    0.59
    MemoryWarning
    0.59
    featureID
    0.57
     @"/
    0.56
     يتيمه
    0.56
    SourceChecksum
    0.55
    nloa
    0.55
    Diweddarwch
    0.54
    Act Density 0.025%

    No Known Activations