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

    Neuronpedia

    INDEX
    Explanations

    advertised on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     savor
    0.64
    flavor
    0.61
     organizing
    0.59
     neighbors
    0.58
    behavior
    0.58
    neighbor
    0.57
     realizing
    0.57
     neighbor
    0.56
    neighbors
    0.56
     swath
    0.56
    POSITIVE LOGITS
     Whilst
    1.20
    Whilst
    1.16
     whilst
    1.12
     standardised
    1.11
     finalised
    1.09
     adverts
    1.08
     recognisable
    1.08
     personalised
    1.06
     instalment
    1.06
     utilises
    1.05
    Act Density 0.010%

    No Known Activations