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

    Neuronpedia

    INDEX
    Explanations

    HTML code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .assertNot
    -0.07
     osm
    -0.06
    øj
    -0.06
    \\\\
    -0.06
    ")+
    -0.06
    ())/
    -0.06
    (Product
    -0.06
    Canvas
    -0.06
     Merk
    -0.06
     Legion
    -0.06
    POSITIVE LOGITS
    swift
    0.07
    ه
    0.07
    О
    0.06
    `)↵
    0.06
    cul
    0.06
     Leaders
    0.06
     اه
    0.06
     Love
    0.06
    keyword
    0.06
    А
    0.06
    Act Density 0.007%

    No Known Activations