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

    Neuronpedia

    INDEX
    Explanations

    gift-giving customs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    מו
    0.55
     oraș
    0.54
    国家的
    0.54
    都
    0.53
    ного
    0.50
    تم
    0.50
    Their
    0.49
    都不是
    0.49
    市民
    0.48
    没有
    0.46
    POSITIVE LOGITS
    am
    0.60
    ment
    0.58
     giving
    0.58
    inim
    0.52
    giving
    0.52
    itute
    0.50
     vadati
    0.50
     ホイールセット
    0.49
     vassal
    0.48
     giver
    0.48
    Act Density 0.000%

    No Known Activations