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

    Neuronpedia

    INDEX
    Explanations

    witnessing events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dorm
    -0.07
     команды
    -0.07
     Pac
    -0.07
    segu
    -0.07
     Left
    -0.07
    방
    -0.07
    leasing
    -0.07
    otion
    -0.07
     команда
    -0.07
    wania
    -0.07
    POSITIVE LOGITS
     firsthand
    0.14
     witnessing
    0.12
     constater
    0.11
    了解到
    0.11
    Witness
    0.11
    看到
    0.11
     witnessed
    0.10
     atrocities
    0.10
     Beob
    0.10
     saddened
    0.10
    Act Density 0.173%

    No Known Activations