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

    Neuronpedia

    INDEX
    Explanations

    the palace, your hand, the schedule

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    0.52
    ↵↵
    0.49
     ocasion
    0.46
     atteinte
    0.46
    ors
    0.44
    ある
    0.43
    ️⃣
    0.42
     Bertha
    0.41
    йон
    0.41
     obtenir
    0.40
    POSITIVE LOGITS
    ز
    0.51
    는
    0.51
    ও
    0.50
    ע
    0.47
    ใน
    0.47
    и
    0.46
    icht
    0.46
    吗
    0.45
    um
    0.44
    गुप्त
    0.43
    Act Density 0.000%

    No Known Activations