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

    Neuronpedia

    INDEX
    Explanations

    **1. What is a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dolore
    0.71
     confirma
    0.71
     confirme
    0.68
     خواهد
    0.61
     majd
    0.61
     തന്നെ
    0.58
     again
    0.57
     confirmar
    0.57
     confirm
    0.56
     Далее
    0.56
    POSITIVE LOGITS
    是一种
    0.87
     essentially
    0.86
     amacıyla
    0.84
    旨在
    0.82
    是一個
    0.82
     बेसिकली
    0.80
    目的是
    0.79
    是一種
    0.79
     brainchild
    0.79
     nhằm
    0.78
    Act Density 0.015%

    No Known Activations