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

    Neuronpedia

    INDEX
    Explanations

    same

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     downs
    -0.07
     THANK
    -0.07
    ück
    -0.07
     mouths
    -0.07
    τία
    -0.07
     chút
    -0.06
     mieux
    -0.06
     Bugün
    -0.06
    creation
    -0.06
     minions
    -0.06
    POSITIVE LOGITS
     电
    0.06
    .Mesh
    0.06
    iche
    0.06
    edium
    0.06
    ิร
    0.06
    
    0.06
    관
    0.05
    /e
    0.05
     commanding
    0.05
    :C
    0.05
    Act Density 0.024%

    No Known Activations