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

    Neuronpedia

    INDEX
    Explanations

    -c

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Suite
    -0.08
    令
    -0.08
     AMD
    -0.07
    仓
    -0.07
     pd
    -0.07
     knex
    -0.07
     더
    -0.07
    죄
    -0.07
    .directive
    -0.07
     Dani
    -0.07
    POSITIVE LOGITS
     Uh
    0.06
    .contents
    0.06
     Zimmerman
    0.05
     Updates
    0.05
    (off
    0.05
    reviews
    0.05
     handbook
    0.05
     Later
    0.05
    .Gray
    0.05
    statements
    0.05
    Act Density 0.000%

    No Known Activations