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

    Neuronpedia

    INDEX
    Explanations

    basic concepts and starting points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ఉన్నాయి
    0.40
    zele
    0.39
                         
    0.37
    ходили
    0.37
    eners
    0.36
     ઉપરા
    0.36
     analysis
    0.35
    ходят
    0.35
     листо
    0.35
    土産
    0.35
    POSITIVE LOGITS
     garantizar
    0.43
     régl
    0.41
    噱
    0.41
     ayud
    0.41
     PlayStation
    0.41
     zapewn
    0.41
     Secrets
    0.41
     açı
    0.40
     lézards
    0.40
     Bhagavato
    0.40
    Act Density 0.002%

    No Known Activations