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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scheduler
    -0.07
    Loss
    -0.06
    ATIONAL
    -0.06
    need
    -0.06
    观看
    -0.06
    ungan
    -0.06
    -fixed
    -0.06
     stimulated
    -0.06
    unger
    -0.06
     deletes
    -0.06
    POSITIVE LOGITS
    yers
    0.06
     вариант
    0.06
     minions
    0.06
     czas
    0.06
     замов
    0.06
     tiế
    0.06
     мис
    0.06
     pokus
    0.06
     наших
    0.06
    born
    0.06
    Act Density 0.174%

    No Known Activations