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

    Neuronpedia

    INDEX
    Explanations

    diverse online content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orge
    -0.07
     Extreme
    -0.07
     mav
    -0.07
     Quartz
    -0.07
    損害
    -0.06
    lav
    -0.06
    激起
    -0.06
     Dr
    -0.06
    ử
    -0.06
    Ver
    -0.06
    POSITIVE LOGITS
    ⌥
    0.07
     mechanically
    0.07
     المع
    0.07
    馕
    0.07
     economically
    0.07
    英格
    0.07
     déf
    0.07
    (short
    0.07
     운
    0.07
     rug
    0.07
    Act Density 0.132%

    No Known Activations