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

    Neuronpedia

    INDEX
    Explanations

    options with parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    銥
    0.52
    綃
    0.52
    磧
    0.51
    釹
    0.50
    TableHeader
    0.50
    杣
    0.49
     drivetrain
    0.49
    並沒有
    0.48
    ักษณะ
    0.48
    鰓
    0.48
    POSITIVE LOGITS
    填
    0.67
    英语
    0.56
    句子
    0.55
     中国
    0.53
    【
    0.53
     【
    0.52
    （
    0.52
    ①
    0.52
     Китай
    0.52
    选择
    0.51
    Act Density 0.003%

    No Known Activations