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

    Neuronpedia

    INDEX
    Explanations

    diagnose how to provide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सबसे
    0.39
     npm
    0.38
     firsthand
    0.38
    一个小
    0.38
    With
    0.38
     मूल्य
    0.38
    एक
    0.38
    Tips
    0.38
     எளி
    0.38
    Uploaded
    0.37
    POSITIVE LOGITS
     pedidos
    0.45
     csoport
    0.45
     họ
    0.45
     soort
    0.44
     têm
    0.44
     kanë
    0.43
    들은
    0.43
     них
    0.43
     mají
    0.43
     imaju
    0.42
    Act Density 0.009%

    No Known Activations