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

    Neuronpedia

    INDEX
    Explanations

    per

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adors
    -0.07
     Yates
    -0.07
    补
    -0.06
    tracks
    -0.06
    Occurs
    -0.06
    etermin
    -0.06
    stant
    -0.06
    Drivers
    -0.06
     almost
    -0.06
     occult
    -0.06
    POSITIVE LOGITS
     Workspace
    0.07
     ))}↵
    0.06
     skl
    0.06
    (inflater
    0.06
    .LOGIN
    0.06
    ],&
    0.06
     फ
    0.06
    ARED
    0.06
    ipherals
    0.06
     displayed
    0.06
    Act Density 0.006%

    No Known Activations