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

    Neuronpedia

    INDEX
    Explanations

    .C

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    帮助
    -0.07
    index
    -0.07
     Module
    -0.07
    Saved
    -0.07
    睚
    -0.07
    ely
    -0.07
    Anchor
    -0.07
    emon
    -0.06
     window
    -0.06
     смож
    -0.06
    POSITIVE LOGITS
     procure
    0.08
    哈尔
    0.08
    𝑲
    0.07
     giấy
    0.07
    資訊
    0.07
     Thông
    0.07
    attended
    0.07
     disposition
    0.07
    glass
    0.07
    יקים
    0.07
    Act Density 0.004%

    No Known Activations