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

    Neuronpedia

    INDEX
    Explanations

    pronoun reference and grammar rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    選舉
    0.77
    閉店
    0.75
     étroites
    0.74
    ى
    0.73
    ू
    0.71
    硼
    0.71
    模拟
    0.69
     draining
    0.69
    過程中
    0.66
    л
    0.66
    POSITIVE LOGITS
    s
    1.00
    вает
    0.83
    themem
    0.77
    ﺸ
    0.77
    klasse
    0.76
    commonByteArray
    0.76
    rukt
    0.74
     специальности
    0.74
     внутрен
    0.73
    ের
    0.73
    Act Density 0.001%

    No Known Activations