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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﹐
    0.48
    裒
    0.47
    埶
    0.44
     mitochondria
    0.43
     calorimetry
    0.42
    伈
    0.42
    存档备份
    0.42
    㣻
    0.42
     dislocations
    0.42
    উল্লেখ
    0.42
    POSITIVE LOGITS
     Seeing
    0.65
    Seeing
    0.62
    ……
    0.54
     seeing
    0.52
    唰
    0.51
    …
    0.48
    !
    0.47
    しかし
    0.46
     Damn
    0.46
    与此同时
    0.46
    Act Density 0.001%

    No Known Activations