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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    te
    -0.07
    کنون
    -0.07
     cops
    -0.07
     Adults
    -0.07
    美國
    -0.07
     IMAGES
    -0.07
    Password
    -0.06
    rica
    -0.06
     Phil
    -0.06
     Maya
    -0.06
    POSITIVE LOGITS
     üretim
    0.07
    (cli
    0.07
    obil
    0.06
     '',
    0.06
     мист
    0.06
    conut
    0.06
    signed
    0.06
     sàng
    0.06
    �认
    0.06
    Seeder
    0.06
    Act Density 0.005%

    No Known Activations