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

    Neuronpedia

    INDEX
    Explanations

    1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    itudes
    0.58
    ᴴ
    0.53
    ූර්
    0.51
    所以
    0.49
    trim
    0.49
    ོས་
    0.49
    0.48
    то
    0.48
    しかも
    0.48
    ফলে
    0.48
    POSITIVE LOGITS
    ंत्रिकी
    0.61
    ه
    0.60
    ğı
    0.57
    in
    0.57
    aaf
    0.56
     फिर
    0.55
    a
    0.53
    вчи
    0.52
    ாச
    0.51
    ﻝ
    0.51
    Act Density 0.771%

    No Known Activations