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

    Neuronpedia

    INDEX
    Explanations

    groups of people involved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Emulator
    0.75
     catheter
    0.73
     annotate
    0.73
     saya
    0.72
     XD
    0.71
     emulator
    0.70
     marinade
    0.69
     X
    0.69
    帮你
    0.67
     voltage
    0.67
    POSITIVE LOGITS
     proponents
    1.19
     economists
    1.03
    esistenza
    1.01
     pundits
    1.01
     theorists
    0.98
     humankind
    0.97
     revolutionaries
    0.97
     policymakers
    0.96
     philosophers
    0.94
    Encycl
    0.94
    Act Density 0.724%

    No Known Activations