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

    Neuronpedia

    INDEX
    Explanations

    people sitting or standing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    成为
    0.41
    成為
    0.36
     تصير
    0.35
     deviennent
    0.34
    变为
    0.33
     diventare
    0.33
    ActionPerformed
    0.33
     අය
    0.32
     reminder
    0.32
     devenir
    0.32
    POSITIVE LOGITS
     sitting
    1.22
     Sitting
    0.96
    sitting
    0.96
    坐在
    0.93
     duduk
    0.93
    Sitting
    0.92
     lounging
    0.92
     ngồi
    0.91
     seated
    0.88
     sipping
    0.88
    Act Density 0.052%

    No Known Activations