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

    Neuronpedia

    INDEX
    Explanations

    acknowledging counterpoints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ла
    0.96
    ້ອງ
    0.79
    निर्माण
    0.74
    ام
    0.72
    êng
    0.71
     सकेंगे
    0.71
    Visualization
    0.69
    イル
    0.68
    rī
    0.67
    ак
    0.66
    POSITIVE LOGITS
     δεν
    0.88
     you
    0.87
     everywhere
    0.83
     اكيد
    0.82
     outweighs
    0.80
     bhi
    0.80
     >
    0.79
     underrated
    0.78
     denen
    0.77
     if
    0.77
    Act Density 0.000%

    No Known Activations