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

    Neuronpedia

    INDEX
    Explanations

    driver information display safety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tag
    0.44
     tag
    0.44
     mainland
    0.40
     fundraising
    0.39
    पीड़
    0.39
     Prêmio
    0.39
    翰
    0.39
     eligible
    0.39
     homemade
    0.39
     invent
    0.39
    POSITIVE LOGITS
     ergonom
    0.98
     operator
    0.97
    operator
    0.96
    Operator
    0.93
     Operator
    0.93
     ergonomics
    0.90
     ergonomic
    0.90
     opérateur
    0.87
    cognitive
    0.84
     workload
    0.83
    Act Density 0.040%

    No Known Activations