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

    Neuronpedia

    INDEX
    Explanations

    government agencies

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spacetime
    0.68
    ProductRunnable
    0.63
     ब्रह्
    0.63
    Rotate
    0.62
     музи
    0.61
    音乐
    0.61
     Newtonian
    0.60
     serendip
    0.60
     continents
    0.57
     constipation
    0.57
    POSITIVE LOGITS
     agency
    2.67
     Agency
    2.52
     agencies
    2.42
    Agency
    2.25
    agency
    2.23
     Agencies
    2.16
     Department
    2.02
     department
    1.98
     AGENCY
    1.95
     agencia
    1.95
    Act Density 0.156%

    No Known Activations