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

    Neuronpedia

    INDEX
    Explanations

    file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    姚明
    -0.08
    팟
    -0.07
    䴘
    -0.07
    zman
    -0.07
    镵
    -0.07
    赑
    -0.07
    hone
    -0.07
    إرسال
    -0.07
    プラス
    -0.07
    天国
    -0.07
    POSITIVE LOGITS
     se
    0.07
     streets
    0.07
     Cuisine
    0.07
     novels
    0.06
    -packed
    0.06
    ARNING
    0.06
    吃到
    0.06
     ST
    0.06
     Physics
    0.06
     обслужива
    0.06
    Act Density 0.007%

    No Known Activations