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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     providing
    -0.07
    Never
    -0.06
     فقط
    -0.06
     FBI
    -0.06
     evil
    -0.06
    模
    -0.06
    Zero
    -0.06
     阿
    -0.06
     BOX
    -0.06
     bottoms
    -0.06
    POSITIVE LOGITS
     Stage
    0.06
    金融
    0.06
     Temmuz
    0.06
    OperationException
    0.06
    ποιη
    0.06
    .FileInputStream
    0.06
    당
    0.06
    _BLEND
    0.06
    PTION
    0.06
    ptom
    0.06
    Act Density 0.018%

    No Known Activations