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
     jde
    -0.07
    WARE
    -0.07
     Neither
    -0.07
     Objects
    -0.07
     여
    -0.07
    izin
    -0.07
    {(
    -0.06
     wealth
    -0.06
     Eisenhower
    -0.06
     Pf
    -0.06
    POSITIVE LOGITS
     CHAPTER
    0.07
     partida
    0.06
    "↵↵↵↵
    0.06
     Colony
    0.06
    .generic
    0.06
     xmm
    0.06
     quot
    0.06
     gimm
    0.06
    Chapter
    0.06
     GDK
    0.06
    Act Density 0.009%

    No Known Activations