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

    Neuronpedia

    INDEX
    Explanations

    etc. / various types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     दो
    0.75
     ње
    0.66
     his
    0.66
     jeho
    0.65
     njegova
    0.64
     ಎರಡು
    0.63
     two
    0.61
     його
    0.61
    明确
    0.61
     jego
    0.59
    POSITIVE LOGITS
    などの
    0.96
     etc
    0.94
    など
    0.93
    等の
    0.80
     ஆகியவற்ற
    0.79
    etc
    0.77
     тощо
    0.76
     প্রভৃতি
    0.75
     등
    0.75
    .)
    0.74
    Act Density 0.017%

    No Known Activations