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

    Neuronpedia

    INDEX
    Explanations

    Code and multiple languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Repair
    -0.07
     EPS
    -0.07
     phrase
    -0.07
     hâlâ
    -0.07
     использования
    -0.06
     아이
    -0.06
    _TV
    -0.06
     horrible
    -0.06
     frustration
    -0.06
     KUR
    -0.06
    POSITIVE LOGITS
    rowser
    0.06
    )],↵
    0.06
     uncle
    0.06
    105
    0.06
    иму
    0.06
     Wishlist
    0.06
    .widget
    0.06
    Votes
    0.06
    olum
    0.06
    (Qt
    0.06
    Act Density 0.003%

    No Known Activations