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

    Neuronpedia

    INDEX
    Explanations

    types of development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    бна
    0.50
     oferece
    0.45
     apresenta
    0.43
     prezent
    0.40
     предлагает
    0.40
     технология
    0.40
    ख़
    0.40
    Tech
    0.39
    шкина
    0.39
    Toolkit
    0.38
    POSITIVE LOGITS
    imeters
    0.40
     sadd
    0.40
    ocity
    0.40
     істо
    0.39
    鎳
    0.39
     sông
    0.38
    笊
    0.38
     Darby
    0.38
     kr
    0.37
     फ्रेंच
    0.37
    Act Density 0.000%

    No Known Activations