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

    Neuronpedia

    INDEX
    Explanations

    arrangement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fe
    -0.07
    /customer
    -0.07
     yi
    -0.07
     Tweets
    -0.07
     IsNot
    -0.07
    _CA
    -0.07
    isu
    -0.07
    여
    -0.07
    _you
    -0.07
     pasado
    -0.07
    POSITIVE LOGITS
     the
    0.07
     a
    0.07
    的
    0.07
     arrangement
    0.07
     permits
    0.07
    칟
    0.07
    Distinct
    0.06
     },
↵
    0.06
     having
    0.06
    愃
    0.06
    Act Density 0.016%

    No Known Activations