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

    Neuronpedia

    INDEX
    Explanations

    sentencing enhancements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Detector
    -0.08
     Hera
    -0.07
     回
    -0.07
     Vil
    -0.06
     Và
    -0.06
    _nodes
    -0.06
     Media
    -0.06
    四
    -0.06
    .Dispatcher
    -0.06
    quina
    -0.06
    POSITIVE LOGITS
    xED
    0.08
    ้ย
    0.07
     fishes
    0.06
    ifton
    0.06
    populate
    0.06
    ислов
    0.06
    call
    0.06
     pickups
    0.06
    prob
    0.06
     채용
    0.06
    Act Density 0.008%

    No Known Activations