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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     منتقل
    0.90
     condivid
    0.79
     የሚያ
    0.75
     демонстри
    0.74
     나타
    0.72
     đem
    0.72
     добавля
    0.70
     갖고
    0.70
     menyampaikan
    0.69
     melakukan
    0.69
    POSITIVE LOGITS
     इसने
    0.56
     dance
    0.54
    ものです
    0.54
     வருக
    0.54
     ભ
    0.52
    ர்ப்ப
    0.51
     വ
    0.51
    oelectronic
    0.49
     plate
    0.48
     ма
    0.48
    Act Density 1.586%

    No Known Activations