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

    Neuronpedia

    INDEX
    Explanations

    data processing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    又
    -0.07
     Maven
    -0.06
    Front
    -0.06
     Clark
    -0.06
    tures
    -0.06
    adden
    -0.06
     Qaeda
    -0.06
    (ip
    -0.06
     Front
    -0.06
     미
    -0.06
    POSITIVE LOGITS
    (vector
    0.07
     UNIVERSITY
    0.07
     手机
    0.06
    .tableView
    0.06
     Businesses
    0.06
    ";
    0.06
    /basic
    0.06
    capture
    0.06
     defaultManager
    0.06
    ,-
    0.06
    Act Density 0.000%

    No Known Activations