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

    Neuronpedia

    INDEX
    Explanations

    left followed by opening bracket

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Graz
    0.69
    wise
    0.67
     &_
    0.66
     ἡ
    0.65
     ļ
    0.65
     फंडा
    0.64
     विक्रय
    0.63
    ེ་
    0.63
     méthode
    0.63
    ದಲ್ಲಿ
    0.62
    POSITIVE LOGITS
    [\
    1.32
    (\
    1.27
    \{\
    1.09
    (-\
    1.01
    |\
    1.01
    \{
    1.00
    [
    0.98
    [-\
    0.93
    (=
    0.80
    ({\
    0.79
    Act Density 0.017%

    No Known Activations