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

    Neuronpedia

    INDEX
    Explanations

    of this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    كُمْ
    0.53
     त्यानंतर
    0.51
    атра
    0.50
    নকে
    0.47
    icularly
    0.47
    tedy
    0.46
     उसे
    0.45
     melakukannya
    0.45
    akala
    0.45
     उसका
    0.44
    POSITIVE LOGITS
     this
    2.13
    this
    2.05
     هذا
    1.84
     questo
    1.78
     acest
    1.77
    この
    1.73
     इस
    1.72
     questa
    1.72
     هذه
    1.67
     această
    1.65
    Act Density 0.989%

    No Known Activations