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

    Neuronpedia

    INDEX
    Explanations

    breakdown of how to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     committed
    0.46
     registered
    0.43
     responsible
    0.43
     celebrated
    0.42
    不但
    0.41
     positively
    0.41
    committed
    0.41
    nicht
    0.40
    truncated
    0.39
     located
    0.39
    POSITIVE LOGITS
    两人
    0.47
     outils
    0.45
     아래
    0.45
    几年
    0.45
    🍋
    0.44
     màu
    0.43
    🌊
    0.42
    三年
    0.42
    NERS
    0.42
    🍩
    0.42
    Act Density 0.011%

    No Known Activations