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

    Neuronpedia

    INDEX
    Explanations

    code structures and quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    च
    0.25
    ฬา
    0.23
     செய்வது
    0.23
    |.|.|
    0.23
    ها
    0.23
    meisterschaft
    0.22
     Josephson
    0.22
    =-\
    0.22
     Pediatric
    0.22
     শরীরের
    0.22
    POSITIVE LOGITS
    ("
    0.47
     "
    0.41
    ="
    0.41
     "@
    0.41
     "__
    0.39
     ["
    0.39
    ('
    0.39
     "$
    0.38
     "????
    0.38
    ['
    0.36
    Act Density 0.278%

    No Known Activations