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

    Neuronpedia

    INDEX
    Explanations

    files and profiles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     override
    -0.07
    stats
    -0.07
    解
    -0.07
    _coords
    -0.07
    vincia
    -0.07
     pubkey
    -0.07
    ?;↵
    -0.07
    aversal
    -0.07
    合法权益
    -0.06
     docker
    -0.06
    POSITIVE LOGITS
     tụ
    0.07
     `.
    0.07
    吸入
    0.07
    otron
    0.07
    quent
    0.07
    (article
    0.07
    柱
    0.06
    ится
    0.06
     Crushers
    0.06
     theft
    0.06
    Act Density 0.002%

    No Known Activations