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

    Neuronpedia

    INDEX
    Explanations

    parentheses, brackets, and quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ']
    0.82
    '/>
    0.75
    ">,</
    0.74
     ';
    0.71
     '/',
    0.70
    ']/
    0.68
    ="/">
    0.68
    '}).
    0.67
    '])
    0.65
    /',
    0.64
    POSITIVE LOGITS
     lui
    0.85
    भूति
    0.84
     him
    0.82
    ಂಥ
    0.79
     diretto
    0.79
    argy
    0.78
    (`#
    0.78
    QtCore
    0.77
    adiator
    0.77
     egli
    0.77
    Act Density 0.102%

    No Known Activations