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

    Neuronpedia

    INDEX
    Explanations

    product descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grasses
    0.71
     myopia
    0.71
     cupcakes
    0.70
     cupcake
    0.69
     mitosis
    0.69
     capitalism
    0.68
     dichos
    0.67
     succulents
    0.67
     gloves
    0.66
     mittens
    0.65
    POSITIVE LOGITS
    Transaksi
    0.69
     乀
    0.64
    Optimal
    0.61
    Movie
    0.60
    Origin
    0.60
    Hasil
    0.60
     чыныгы
    0.60
    ផលិត
    0.59
    Honor
    0.59
    Galer
    0.59
    Act Density 0.008%

    No Known Activations