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

    Neuronpedia

    INDEX
    Explanations

    exercise arm and leg

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     probabilmente
    0.83
    ی
    0.82
     б
    0.82
     сти
    0.80
    یط
    0.79
     intorno
    0.79
     quadrants
    0.78
    𝘦
    0.78
     е
    0.77
     дисци
    0.77
    POSITIVE LOGITS
    ကောင်း
    0.81
    age
    0.75
    iter
    0.74
    statt
    0.73
    ibley
    0.73
     laugh
    0.72
    ంటు
    0.70
     Olympic
    0.69
     CMO
    0.68
     Hollywood
    0.68
    Act Density 0.002%

    No Known Activations