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

    Neuronpedia

    INDEX
    Explanations

    ratio, identity, quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     patriarchal
    0.80
     autocratic
    0.72
     cosidd
    0.71
    democracy
    0.70
     racism
    0.70
    ethnic
    0.69
     militias
    0.69
     isch
    0.68
     ethnic
    0.67
     ಗೌ
    0.67
    POSITIVE LOGITS
     içeren
    0.85
     diterapkan
    0.74
    添加到
    0.73
     MacBook
    0.72
     सब्स
    0.70
     Macbook
    0.69
    然后在
    0.67
     மதுரை
    0.67
    мум
    0.66
     Imported
    0.65
    Act Density 0.563%

    No Known Activations