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

    Neuronpedia

    INDEX
    Explanations

    personal attributes and history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    它们的
    0.72
    Balances
    0.59
    Shapes
    0.57
    áneas
    0.57
     Collectively
    0.57
     저장
    0.56
     résultat
    0.56
     niiden
    0.56
     Bereichen
    0.55
    Types
    0.55
    POSITIVE LOGITS
     abilities
    0.95
     actions
    0.94
     demeanor
    0.87
     backstory
    0.87
     plight
    0.86
     upbringing
    0.86
     predicament
    0.86
     presence
    0.86
     identity
    0.81
     own
    0.81
    Act Density 0.721%

    No Known Activations