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

    Neuronpedia

    INDEX
    Explanations

    Agency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stout
    -0.07
     을
    -0.06
     친
    -0.06
    (Content
    -0.06
    .Render
    -0.06
    ριστ
    -0.06
    addin
    -0.06
    -Con
    -0.06
     climbers
    -0.06
     прост
    -0.06
    POSITIVE LOGITS
     agencies
    0.10
     agency
    0.10
     Agency
    0.10
     Agencies
    0.09
    agency
    0.09
    Agency
    0.09
     agents
    0.08
     agent
    0.07
     Ferguson
    0.07
     nexus
    0.07
    Act Density 0.007%

    No Known Activations