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

    Neuronpedia

    INDEX
    Explanations

    lists of activities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     careless
    -0.09
     лицо
    -0.09
     gmail
    -0.09
     созн
    -0.08
     aí
    -0.08
     exprim
    -0.08
     считать
    -0.08
     consp
    -0.08
    .Adam
    -0.08
     dívida
    -0.08
    POSITIVE LOGITS
     guests
    0.11
     amenities
    0.11
    特色
    0.11
     festivities
    0.10
     stattfinden
    0.10
     attendees
    0.10
     exhibitors
    0.10
     featuring
    0.10
     workshops
    0.10
     развлеч
    0.10
    Act Density 0.137%

    No Known Activations