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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Orth
    -0.07
     наиболее
    -0.07
    046
    -0.07
    QUESTION
    -0.07
     çoğu
    -0.06
    665
    -0.06
     oldValue
    -0.06
     输出
    -0.06
    lbrace
    -0.06
     enriched
    -0.06
    POSITIVE LOGITS
     generously
    0.07
    reating
    0.07
     зм
    0.06
    .ConnectionStrings
    0.06
     marry
    0.06
    .home
    0.06
    개를
    0.06
    ßer
    0.06
    ichen
    0.06
    .cell
    0.06
    Act Density 0.008%

    No Known Activations