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

    Neuronpedia

    INDEX
    Explanations

    original

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CLE
    -0.08
     cleansing
    -0.07
     Ingredients
    -0.07
     statue
    -0.07
    UniqueId
    -0.07
     carved
    -0.07
    été
    -0.07
    (force
    -0.06
     newPassword
    -0.06
    duced
    -0.06
    POSITIVE LOGITS
    🖱
    0.08
    갹
    0.07
    쟀
    0.06
     Dropbox
    0.06
    >>(↵
    0.06
    customerId
    0.06
    ighet
    0.06
    뇩
    0.06
    memory
    0.06
    ӟ
    0.06
    Act Density 0.001%

    No Known Activations