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

    Neuronpedia

    INDEX
    Explanations

    words indicating familial relationships or titles, along with connecting words like "and" or "of"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     &___
    -0.89
    Personensuche
    -0.82
     BoxFit
    -0.81
     kids
    -0.78
     onCancelled
    -0.74
    setupUi
    -0.73
     children
    -0.71
    quelize
    -0.71
    GEBURTSDATUM
    -0.70
    findpost
    -0.70
    POSITIVE LOGITS
     second
    0.53
     Second
    0.53
     former
    0.50
     protégé
    0.50
     colleague
    0.50
    th
    0.47
    Second
    0.45
     friend
    0.45
     teammate
    0.45
     protege
    0.44
    Act Density 1.334%

    No Known Activations