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

    Neuronpedia

    INDEX
    Explanations

    butter, softened, melted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nanjing
    0.42
    吊
    0.42
     قبر
    0.42
     подве
    0.41
    لقة
    0.40
    ົງ
    0.39
     معي
    0.38
     SPINE
    0.38
     OnTrigger
    0.38
    ulfate
    0.37
    POSITIVE LOGITS
     butter
    1.78
    Butter
    1.63
    butter
    1.61
     Butter
    1.59
    バター
    1.41
    🧈
    1.37
     buttery
    1.28
     beurre
    1.22
     margarine
    0.93
     Butterworth
    0.92
    Act Density 0.030%

    No Known Activations