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

    Neuronpedia

    INDEX
    Explanations

    possible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (decimal
    -0.07
    .rating
    -0.07
    /router
    -0.06
    (table
    -0.06
    ....
    -0.06
     james
    -0.06
     детей
    -0.06
     иму
    -0.06
    .Replace
    -0.06
     jas
    -0.06
    POSITIVE LOGITS
    考え
    0.07
    лях
    0.07
    ินทาง
    0.07
     rencontrer
    0.07
     possible
    0.07
    HN
    0.06
    ACP
    0.06
    Poss
    0.06
    가지
    0.06
     Propel
    0.06
    Act Density 0.018%

    No Known Activations