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

    Neuronpedia

    INDEX
    Explanations

    CA Key Blind Time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vist
    0.51
     продаж
    0.47
     Schools
    0.44
     Viv
    0.44
     Criminal
    0.42
    दृश्य
    0.42
     genie
    0.40
     schools
    0.38
     Is
    0.38
    ابعة
    0.37
    POSITIVE LOGITS
    咽
    0.40
     لکھنے
    0.39
    新建
    0.38
    观看
    0.38
    (||
    0.38
    \{\
    0.38
    杀死
    0.37
     紹介
    0.37
    writers
    0.37
    throughput
    0.36
    Act Density 0.000%

    No Known Activations