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

    Neuronpedia

    INDEX
    Explanations

    closing parenthesis followed by conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     （
    0.99
     (
    0.98
    （
    0.94
     (/
    0.80
     (\
    0.74
     ()
    0.69
     ({\
    0.69
    ！（
    0.68
     (_
    0.66
     '(
    0.65
    POSITIVE LOGITS
    ﻤ
    0.48
    亟
    0.45
    YNAMIC
    0.45
    များနှင့်
    0.45
    ត្រូវការ
    0.45
    IFORNIA
    0.44
    ﻨ
    0.44
    跃
    0.44
    ONS
    0.43
    SQLite
    0.43
    Act Density 0.132%

    No Known Activations