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

    Neuronpedia

    INDEX
    Explanations

    comparisons with than or as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    osal
    0.43
    到一个
    0.42
    はん
    0.41
    通常の
    0.39
     فيديو
    0.39
     দেখলাম
    0.39
    饼
    0.39
    などの
    0.38
     Sử
    0.38
    📹
    0.38
    POSITIVE LOGITS
     ours
    0.68
     hers
    0.66
     theirs
    0.64
     Ours
    0.57
     milik
    0.49
     quello
    0.48
     mine
    0.47
     counterpart
    0.46
     yours
    0.44
     celui
    0.42
    Act Density 0.069%

    No Known Activations