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

    Neuronpedia

    INDEX
    Explanations

    comma and colon separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kristall
    0.49
     आबादी
    0.45
     gonad
    0.45
     chrét
    0.44
     sommer
    0.43
     wych
    0.43
     spekt
    0.42
     struktur
    0.41
    ประสบ
    0.41
     atlet
    0.40
    POSITIVE LOGITS
    分隔
    0.59
     separator
    0.55
    delimiter
    0.55
    separator
    0.53
     separators
    0.53
    comma
    0.52
    split
    0.51
     delimiter
    0.51
     delimiters
    0.49
    String
    0.47
    Act Density 0.076%

    No Known Activations