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

    Neuronpedia

    INDEX
    Explanations

    Renaissance governance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trivially
    0.61
     suboptimal
    0.61
     Calyce
    0.60
     quantifying
    0.59
    Quaternion
    0.59
    Bracketing
    0.55
    参数
    0.54
    遍历
    0.54
     parámetros
    0.52
     hyperlocal
    0.52
    POSITIVE LOGITS
    government
    0.51
     government
    0.49
     American
    0.48
     landowners
    0.48
     Americans
    0.46
     Britain
    0.46
     ________
    0.46
     colonies
    0.45
    riters
    0.45
    0.45
    Act Density 0.105%

    No Known Activations