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

    Neuronpedia

    INDEX
    Explanations

    Node.js module imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     slightly
    1.04
     tro
    0.94
     desired
    0.93
     arXiv
    0.91
     afar
    0.86
     кел
    0.86
    ตาย
    0.86
     Slightly
    0.84
     tournament
    0.84
     perceived
    0.84
    POSITIVE LOGITS
    ('./
    1.54
    ("./
    1.47
    ('../
    1.27
    ("../
    1.17
    ('@
    1.11
    (`./
    1.07
    ('
    1.05
    ("../../
    0.98
    (@"
    0.98
    ('../../
    0.97
    Act Density 0.002%

    No Known Activations