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

    Neuronpedia

    INDEX
    Explanations

    would like/be/become

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     for
    1.13
     by
    0.96
    uk
    0.91
    er
    0.89
    im
    0.87
    és
    0.87
    at
    0.86
    for
    0.86
    om
    0.84
    ма
    0.84
    POSITIVE LOGITS
    は
    1.16
    는
    1.06
    是
    0.94
    ۔
    0.93
    จะ
    0.93
    ;
    0.90
    কে
    0.89
    のための
    0.89
    の
    0.87
    та
    0.86
    Act Density 0.363%

    No Known Activations