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

    Neuronpedia

    INDEX
    Explanations

    sovereign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ["@
    -0.07
    �
    -0.06
    .attrib
    -0.06
     대
    -0.06
     testers
    -0.06
     URL
    -0.06
     JSON
    -0.06
    -links
    -0.06
    _rename
    -0.06
     response
    -0.06
    POSITIVE LOGITS
     sovereign
    0.09
    Cover
    0.07
    graded
    0.07
    cers
    0.06
     Sovere
    0.06
    chants
    0.06
    273
    0.06
    臣
    0.06
    imizde
    0.06
     constrain
    0.06
    Act Density 0.002%

    No Known Activations