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

    Neuronpedia

    INDEX
    Explanations

    json object structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    诸
    0.53
     ثم
    0.51
     የተለያዩ
    0.51
     ወይም
    0.51
    प्तान
    0.47
    َی
    0.47
    قیه
    0.47
    thedocs
    0.47
    ؟.
    0.46
     وړاند
    0.46
    POSITIVE LOGITS
     εφαρ
    0.39
     efter
    0.38
     seo
    0.38
    After
    0.37
     dopo
    0.37
     après
    0.37
     network
    0.36
     after
    0.36
     univers
    0.35
    ङ्
    0.35
    Act Density 0.002%

    No Known Activations