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

    Neuronpedia

    INDEX
    Explanations

    us

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     booster
    -0.06
     Continent
    -0.06
     bä
    -0.06
     Evropské
    -0.06
    otes
    -0.06
    jong
    -0.06
    _yellow
    -0.06
     toto
    -0.06
    GEN
    -0.06
    RAY
    -0.06
    POSITIVE LOGITS
     Мас
    0.07
    .Authorization
    0.07
    .US
    0.07
    .Application
    0.06
     us
    0.06
     concluding
    0.06
     authored
    0.06
    ("."
    0.06
     University
    0.06
    (END
    0.06
    Act Density 0.010%

    No Known Activations