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

    Neuronpedia

    INDEX
    Explanations

    lists of food

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DUI
    1.16
    el
    1.13
     disgu
    1.13
    ş
    1.09
    OD
    1.05
     sturdy
    1.04
     lifeline
    1.04
    в
    1.01
     hydroly
    0.98
     radish
    0.97
    POSITIVE LOGITS
    𝗙
    1.25
    芏
    1.20
    ️⃣
    1.18
    ీ
    1.16
    습니다
    1.10
    𝗖
    1.10
    ي
    1.05
    ли
    1.00
     excelencia
    1.00
    ية
    1.00
    Act Density 0.047%

    No Known Activations