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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    using
    -0.06
    ýn
    -0.06
    Ban
    -0.05
    -circle
    -0.05
     cupid
    -0.05
    lém
    -0.05
    坐
    -0.05
    .ba
    -0.05
     dest
    -0.05
     Bing
    -0.05
    POSITIVE LOGITS
     attempted
    0.08
     Trans
    0.07
     Loy
    0.07
     scholarships
    0.07
    comparison
    0.07
    ประม
    0.07
    GOR
    0.07
     toilets
    0.07
    (土
    0.07
    imid
    0.07
    Act Density 0.024%

    No Known Activations