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

    Neuronpedia

    INDEX
    Explanations

    production car, doctrine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pertanto
    0.52
    ింది
    0.52
     fars
    0.44
     critical
    0.44
    ihe
    0.44
    aughters
    0.44
     hii
    0.43
     splinter
    0.43
    י
    0.43
     priorities
    0.43
    POSITIVE LOGITS
    ciąż
    0.46
    时间
    0.41
    á
    0.41
     პარ
    0.40
    ঁর
    0.40
    ńskim
    0.39
     पदार्
    0.39
    ó
    0.38
    ál
    0.38
     시간에
    0.38
    Act Density 0.006%

    No Known Activations