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

    Neuronpedia

    INDEX
    Explanations

    elaborate further

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    である
    0.85
    шинство
    0.71
    യിലാണ്
    0.71
     وہی
    0.67
     である
    0.67
     〢
    0.67
     predecessor
    0.66
     namesake
    0.66
     sì
    0.66
    unlike
    0.64
    POSITIVE LOGITS
     further
    6.06
    further
    5.26
     Further
    5.21
    Further
    5.21
    进一步
    4.58
     FURTHER
    4.53
     weitere
    3.87
     weiteren
    3.79
     farther
    3.75
    さらに
    3.69
    Act Density 0.538%

    No Known Activations