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

    Neuronpedia

    INDEX
    Explanations

    step-by-step instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    odings
    0.43
    គ្មាន
    0.39
    origData
    0.37
     expiring
    0.37
    匹
    0.37
     შესახებ
    0.36
    ত্ত্ব
    0.35
    ેલી
    0.34
    这点
    0.34
    モチーフ
    0.34
    POSITIVE LOGITS
     steps
    2.22
     Steps
    2.13
    Steps
    2.11
    steps
    2.08
    步驟
    2.06
    步骤
    2.05
     étapes
    1.98
     langkah
    1.86
    ステップ
    1.79
    ขั้นตอน
    1.77
    Act Density 0.061%

    No Known Activations