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

    Neuronpedia

    INDEX
    Explanations

    jobs, positions, roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Device
    0.38
     инстру
    0.37
    device
    0.35
     vins
    0.35
    到达
    0.35
    Deployed
    0.34
     functionality
    0.34
    Effective
    0.34
     efficaces
    0.34
    ೂರ್
    0.33
    POSITIVE LOGITS
     jobs
    1.59
     positions
    1.55
    positions
    1.32
     позиции
    1.31
    jobs
    1.28
     posiciones
    1.26
     Positions
    1.24
     roles
    1.23
    Positions
    1.23
    职位
    1.21
    Act Density 0.084%

    No Known Activations