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

    Neuronpedia

    INDEX
    Explanations

    CL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ft
    -0.08
     spite
    -0.07
    ə
    -0.07
    ipse
    -0.07
    n
    -0.07
    愧
    -0.07
    ,set
    -0.07
    ILITY
    -0.07
    𝐚
    -0.07
    自驾
    -0.07
    POSITIVE LOGITS
     *>(
    0.08
     halkın
    0.07
    などの
    0.07
     *>
    0.07
    𝐖
    0.07
    炟
    0.07
    小姑娘
    0.06
    QUAL
    0.06
     visualize
    0.06
    を目
    0.06
    Act Density 0.007%

    No Known Activations