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

    Neuronpedia

    INDEX
    Explanations

    agreements and rights

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adress
    -0.07
     VALUES
    -0.06
     supreme
    -0.06
     uzavř
    -0.06
     welcome
    -0.06
     řed
    -0.06
     numbers
    -0.06
     racism
    -0.06
     wardrobe
    -0.06
    retched
    -0.06
    POSITIVE LOGITS
    ContentPane
    0.06
    划
    0.06
     forgiving
    0.06
    Them
    0.06
    donnees
    0.06
    lete
    0.06
     predis
    0.06
     Fluent
    0.06
     %@
    0.06
    -cert
    0.06
    Act Density 0.025%

    No Known Activations