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

    Neuronpedia

    INDEX
    Explanations

    services and facilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dehuman
    0.47
     consequential
    0.42
     meaningless
    0.40
     argues
    0.40
     computationally
    0.40
     decrement
    0.40
     consequ
    0.39
     cognit
    0.39
     iteratively
    0.38
     stoichi
    0.38
    POSITIVE LOGITS
     restrooms
    1.05
     cafes
    1.01
     café
    0.96
     cafe
    0.95
     cafés
    0.95
     Café
    0.91
     kiosks
    0.90
     Cafe
    0.87
     refreshments
    0.86
     vending
    0.86
    Act Density 0.015%

    No Known Activations