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

    Neuronpedia

    INDEX
    Explanations

    anonymous function or lambda

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    工艺
    1.09
    ί
    0.99
    ύ
    0.97
    景象
    0.95
     angiography
    0.93
    Η
    0.89
    )，
    0.88
    飞
    0.88
    ની
    0.85
    )。
    0.83
    POSITIVE LOGITS
    n
    1.19
    ن
    1.02
    an
    1.00
    el
    0.98
    ᵒ
    0.94
    нды
    0.91
    quela
    0.91
     En
    0.90
    न
    0.89
    কালের
    0.87
    Act Density 0.006%

    No Known Activations