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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ：↵↵
    -0.07
    ibName
    -0.07
     subTitle
    -0.07
     şeyler
    -0.06
    riers
    -0.06
    شان
    -0.06
    .about
    -0.06
    。，
    -0.06
     staveb
    -0.06
     саме
    -0.06
    POSITIVE LOGITS
    ская
    0.07
     revelation
    0.06
    訪
    0.06
    \M
    0.06
     crist
    0.06
    conduct
    0.06
     govern
    0.06
     podařilo
    0.06
    ABC
    0.06
    合作
    0.06
    Act Density 0.202%

    No Known Activations