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

    Neuronpedia

    INDEX
    Explanations

    telling/remembering what was said

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     東
    -0.06
     showAlert
    -0.06
     SEX
    -0.06
    谢
    -0.06
    圖
    -0.06
    ク
    -0.06
    _DMA
    -0.06
    496
    -0.06
    혼
    -0.05
     �
    -0.05
    POSITIVE LOGITS
     veniam
    0.06
     国家
    0.06
    概念
    0.06
    ician
    0.06
    ább
    0.06
     cuenta
    0.06
    -chat
    0.06
     palp
    0.06
     Seed
    0.06
     varying
    0.06
    Act Density 0.005%

    No Known Activations