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

    Neuronpedia

    INDEX
    Explanations

    lack of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ໃຊ
    0.57
     かわいい
    0.53
     এটাও
    0.53
    loadNpm
    0.51
    ىلى
    0.51
    ایط
    0.49
     Изда
    0.49
     outlying
    0.49
     chcesz
    0.49
    его
    0.48
    POSITIVE LOGITS
    i
    0.75
     ਇੱਕ
    0.64
    )
    0.61
    '
    0.59
     of
    0.59
    :
    0.59
    ي
    0.57
    י
    0.55
     близо
    0.55
     σε
    0.55
    Act Density 0.027%

    No Known Activations