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

    Neuronpedia

    INDEX
    Explanations

    storage spaces, basements, garages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dining
    0.94
     dining
    0.94
    Dining
    0.92
    Eating
    0.90
     Caf
    0.86
     Eating
    0.86
    dining
    0.83
     cafeter
    0.81
     eating
    0.81
    食堂
    0.80
    POSITIVE LOGITS
     storage
    1.05
     basement
    0.97
     shed
    0.95
    storage
    0.94
    Bas
    0.93
    bas
    0.92
     bas
    0.91
     Storage
    0.87
    倉庫
    0.86
    Storage
    0.85
    Act Density 0.045%

    No Known Activations