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

    Neuronpedia

    INDEX
    Explanations

    best vacation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    来看看
    -1.63
    哙
    -1.59
    缑
    -1.58
    飈
    -1.57
     amelyek
    -1.55
    黼
    -1.55
     cei
    -1.51
    ⃑
    -1.50
     verschillende
    -1.49
     sabid
    -1.48
    POSITIVE LOGITS
    6
    2.48
    8
    2.23
    9
    2.03
    ↵
    1.98
    4
    1.97
    7
    1.94
    There
    1.91
    5
    1.87
    3
    1.86
    If
    1.84
    Act Density 0.004%

    No Known Activations