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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "you" and its variations in conjunction with modal verbs

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

    you can see

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mijne
    -0.61
    routeProvider
    -0.54
    zelfde
    -0.52
     doméstica
    -0.50
    expandindo
    -0.48
     disambiguazione
    -0.48
     griega
    -0.48
     Infór
    -0.48
    ReusableCell
    -0.47
     ostavi
    -0.47
    POSITIVE LOGITS
     you
    0.54
    SFD
    0.45
     GES
    0.43
    Algo
    0.42
    munk
    0.41
    You
    0.41
     RSC
    0.41
     FIS
    0.40
     Tear
    0.40
    тс
    0.40
    Act Density 0.009%

    No Known Activations