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

    Neuronpedia

    INDEX
    Explanations

    phrase completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     результата
    0.57
     exponencial
    0.51
     отчет
    0.50
     شیع
    0.50
     אות
    0.50
     εν
    0.50
     insights
    0.49
     شدید
    0.47
     दट
    0.47
     وتم
    0.47
    POSITIVE LOGITS
     güvenlik
    0.44
     perplexing
    0.44
    ാൻ
    0.43
     çö
    0.42
    ের
    0.41
    ãy
    0.40
     Reserve
    0.40
     හි
    0.40
     hardware
    0.39
     wohl
    0.39
    Act Density 0.000%

    No Known Activations