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

    Neuronpedia

    INDEX
    Explanations

    passive voice and sentence objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    创意
    0.50
    leşt
    0.50
    爆
    0.48
    update
    0.48
    1
    0.47
    ەت
    0.47
    json
    0.47
    Boom
    0.47
    Switch
    0.46
    startup
    0.46
    POSITIVE LOGITS
     batsmen
    0.63
     transactions
    0.52
     multiple
    0.52
     punishments
    0.52
     batters
    0.51
     scorers
    0.50
     linemen
    0.50
    多人
    0.49
     multicellular
    0.49
     kinds
    0.47
    Act Density 0.001%

    No Known Activations