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

    Neuronpedia

    INDEX
    Explanations

    brackets and braces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quitt
    0.41
     breather
    0.40
    लोड
    0.40
    ZT
    0.39
     dusting
    0.39
     tabletop
    0.38
     amen
    0.38
     ega
    0.38
    擢
    0.38
     snowball
    0.38
    POSITIVE LOGITS
     brackets
    2.03
     parentheses
    1.88
     bracket
    1.86
    括号
    1.76
     parenthesis
    1.71
    brackets
    1.67
    bracket
    1.66
    Bracket
    1.56
     Bracket
    1.55
     ब्रैकेट
    1.51
    Act Density 0.071%

    No Known Activations