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

    Neuronpedia

    INDEX
    Explanations

    desserts, food recipes, and taste

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಗೊಳ್ಳ
    0.54
     озе
    0.52
     起
    0.50
    сон
    0.48
     効果
    0.48
     駅
    0.48
    сы
    0.47
     市
    0.46
     速
    0.46
     ಧ
    0.46
    POSITIVE LOGITS
    ري
    0.48
    Bytes
    0.44
    ellant
    0.42
     Ben
    0.40
    re
    0.39
    Ben
    0.39
    donate
    0.39
     dobre
    0.39
    idine
    0.39
     constitue
    0.39
    Act Density 0.000%

    No Known Activations