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

    Neuronpedia

    INDEX
    Explanations

    parameters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    牌
    -0.08
    ني
    -0.07
    ometers
    -0.07
    ttl
    -0.07
     punt
    -0.07
     месяц
    -0.06
     checking
    -0.06
     impr
    -0.06
    tant
    -0.06
     natuur
    -0.06
    POSITIVE LOGITS
     sırasında
    0.08
     SERVER
    0.07
    Shar
    0.07
     SearchResult
    0.07
    收割
    0.07
    Transactional
    0.07
    (storage
    0.07
    (targetEntity
    0.07
    샵
    0.07
    ය
    0.07
    Act Density 0.000%

    No Known Activations