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

    Neuronpedia

    INDEX
    Explanations

    us url paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Laund
    0.62
     Marrakech
    0.61
     టీ
    0.60
    Turkish
    0.60
    堺
    0.59
     Turkish
    0.59
     treadmill
    0.59
    atherapy
    0.58
    urger
    0.58
    上述
    0.57
    POSITIVE LOGITS
     Ig
    1.07
     Eze
    1.02
     Eg
    0.95
     Ok
    0.94
    Ik
    0.91
     Ik
    0.91
    Ig
    0.89
    Eg
    0.89
     Uk
    0.87
     Ih
    0.83
    Act Density 0.037%

    No Known Activations