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

    Neuronpedia

    INDEX
    Explanations

    cell at, a breakthrough

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    throughput
    0.49
     currants
    0.48
    olites
    0.48
    olding
    0.48
     thermoelectric
    0.47
    liced
    0.47
    onden
    0.47
    otyping
    0.47
    undo
    0.46
    oled
    0.46
    POSITIVE LOGITS
    瑜
    0.49
     Eligible
    0.48
    孩子的
    0.47
     Christy
    0.46
    孩子
    0.46
    之中
    0.46
    Ela
    0.45
     Feminist
    0.45
    这
    0.45
    侧
    0.45
    Act Density 0.000%

    No Known Activations