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

    Neuronpedia

    INDEX
    Explanations

    Whom It May Concern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。.
    0.55
     for
    0.54
     bạn
    0.52
    snail
    0.51
    。,
    0.50
    割引
    0.49
     হচ্ছেন
    0.49
    သော
    0.49
    raises
    0.49
    ႃႇ
    0.48
    POSITIVE LOGITS
    '
    0.73
    }
    0.70
    ↵
    0.70
    ]
    0.64
    )
    0.62
    </h2>
    0.59
     empires
    0.55
    (
    0.54
     Bunun
    0.52
    ↵↵
    0.52
    Act Density 0.000%

    No Known Activations