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

    Neuronpedia

    INDEX
    Explanations

    whilst introducing purpose or condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     și
    0.79
     behavior
    0.73
     enggak
    0.70
     ș
    0.70
     определён
    0.70
    behavior
    0.68
     трёх
    0.68
     unauthorized
    0.67
     behaviors
    0.66
    Neighbors
    0.66
    POSITIVE LOGITS
     Whilst
    1.62
    Whilst
    1.55
     whilst
    1.52
     utilises
    1.47
     utilising
    1.36
     emphasises
    1.32
     utilise
    1.30
     utilised
    1.27
     emphasise
    1.27
     recognises
    1.24
    Act Density 0.015%

    No Known Activations