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

    Neuronpedia

    INDEX
    Explanations

    plant growthGolden Globesdata dialogue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ко
    0.80
    Ā
    0.71
    м
    0.70
     научно
    0.65
     jurisprudence
    0.63
    бе
    0.62
     употре
    0.62
    ке
    0.61
     попа
    0.61
    ту
    0.60
    POSITIVE LOGITS
    )，
    0.84
    鏝
    0.82
    <unused173>
    0.82
    分裂
    0.80
    液
    0.80
    "，
    0.79
    )。
    0.74
    泼
    0.74
    rared
    0.73
     Cavs
    0.73
    Act Density 0.130%

    No Known Activations