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

    Neuronpedia

    INDEX
    Explanations

    Roman Empire, intelligence discipline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     اخر
    1.02
     آخر
    0.93
     هم
    0.92
     compat
    0.91
     أ
    0.89
     esetén
    0.89
     با
    0.89
     Из
    0.87
    ೀತ
    0.84
     galore
    0.83
    POSITIVE LOGITS
     hierarchy
    1.18
     system
    1.12
     realm
    1.11
     playbook
    1.05
     subsystem
    1.04
     agenda
    1.02
     microbiome
    1.02
     regime
    0.98
     process
    0.98
     palette
    0.95
    Act Density 1.508%

    No Known Activations