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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     çarp
    -0.07
     ward
    -0.07
    -alist
    -0.06
     Ал
    -0.06
    ораз
    -0.06
    .stdout
    -0.06
    배송
    -0.06
    312
    -0.06
    ategies
    -0.06
    ृ
    -0.06
    POSITIVE LOGITS
     galaxies
    0.06
     libr
    0.06
    DOCUMENT
    0.06
    prises
    0.06
     inform
    0.06
     latency
    0.06
    ||↵
    0.06
    Visit
    0.06
    ..↵
    0.06
     frei
    0.06
    Act Density 0.000%

    No Known Activations