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

    Neuronpedia

    INDEX
    Explanations

    outraged indignation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    1.50
    ９
    1.08
    1.05
    9
    0.91
     раздел
    0.87
    ти
    0.86
    ༦
    0.86
     важ
    0.86
    ↵↵↵↵
    0.85
    ﮨ
    0.85
    POSITIVE LOGITS
    in
    1.34
    í
    1.32
    রা
    1.27
    the
    1.23
    ia
    1.23
    ul
    1.19
    g
    1.19
    m
    1.17
    s
    1.14
    ina
    1.13
    Act Density 0.001%

    No Known Activations