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

    Neuronpedia

    INDEX
    Explanations

    Russian

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adamente
    -0.07
     있던
    -0.07
    운데
    -0.07
    ुमत
    -0.07
    -network
    -0.07
    togroup
    -0.06
     village
    -0.06
    languages
    -0.06
     其
    -0.06
    其
    -0.06
    POSITIVE LOGITS
    479
    0.08
     maxValue
    0.07
    .el
    0.07
    463
    0.06
     narr
    0.06
     BBQ
    0.06
    529
    0.06
    (before
    0.06
    xmin
    0.06
     ↵↵↵↵↵
    0.06
    Act Density 0.034%

    No Known Activations