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

    Neuronpedia

    INDEX
    Explanations

    biographical details about people's education and professional backgrounds

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

    member, degrees, practicing, writer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bürger
    -0.37
    なんとか
    -0.35
     design
    -0.33
     weird
    -0.33
     jarring
    -0.33
    sia
    -0.32
     degenerate
    -0.32
     anything
    -0.31
     inevitable
    -0.31
    ™
    -0.30
    POSITIVE LOGITS
     Normdatei
    0.79
     Réponses
    0.74
    initializeApp
    0.61
     חיצוניים
    0.60
    httphttps
    0.58
     الحره
    0.58
    rungsseite
    0.58
    PyExc
    0.58
    ftagPool
    0.57
     שוליים
    0.56
    Act Density 0.035%

    No Known Activations