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

    Neuronpedia

    INDEX
    Explanations

    CEO

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    侵
    -0.07
     impart
    -0.07
    扭
    -0.07
     patch
    -0.07
     of
    -0.07
    上年
    -0.07
    cred
    -0.07
     infer
    -0.07
    .Manifest
    -0.07
     forbidden
    -0.07
    POSITIVE LOGITS
    DAO
    0.07
     CEO
    0.07
     kvinder
    0.07
     UserDao
    0.07
     יעל
    0.07
    📣
    0.07
     repealed
    0.07
     mechan
    0.06
    liga
    0.06
     될
    0.06
    Act Density 0.007%

    No Known Activations