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

    Neuronpedia

    INDEX
    Explanations

    context of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    роки
    0.52
     Джей
    0.50
     трех
    0.49
     அனைத்து
    0.49
    Người
    0.49
    Ngày
    0.47
    Quién
    0.47
    骑士
    0.47
    Nelson
    0.47
     செயலா
    0.45
    POSITIVE LOGITS
     examples
    0.53
     quantitative
    0.47
     en
    0.47
     prevalent
    0.47
     sites
    0.46
     such
    0.45
     org
    0.44
     diverse
    0.43
     qualitative
    0.43
     a
    0.41
    Act Density 0.009%

    No Known Activations