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

    Neuronpedia

    INDEX
    Explanations

    office of government roles and departments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    شاف
    0.38
    となる
    0.38
    오는
    0.37
     trees
    0.36
     અમે
    0.36
    オーク
    0.36
     छुपा
    0.36
     vient
    0.35
     grasped
    0.35
     washing
    0.35
    POSITIVE LOGITS
     Deputy
    0.54
    Deputy
    0.53
     Solicitor
    0.52
     Commissioner
    0.52
     Ombudsman
    0.48
     Attorney
    0.47
     Comptroller
    0.46
     solicitor
    0.46
     Secretary
    0.45
     deputy
    0.45
    Act Density 0.002%

    No Known Activations