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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     veamos
    0.41
     aesthetically
    0.39
    閇
    0.39
    紾
    0.38
    其次
    0.38
     prestación
    0.38
    荕
    0.38
    娀
    0.37
    柅
    0.37
     그리고
    0.36
    POSITIVE LOGITS
    .
    0.62
    :
    0.57
    ;
    0.55
    ,
    0.43
    {
    0.40
    ।
    0.38
    !
    0.38
    ."
    0.38
    '
    0.37
    。
    0.37
    Act Density 0.003%

    No Known Activations