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

    Neuronpedia

    INDEX
    Explanations

    action before lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cuando
    0.49
     licenc
    0.48
    olian
    0.47
    ourtney
    0.47
    licensed
    0.46
    omis
    0.46
    avacan
    0.46
     आयुर्वेदिक
    0.46
    গাঁও
    0.45
    arat
    0.45
    POSITIVE LOGITS
     funnel
    0.48
     last
    0.46
     empty
    0.45
     Duplicate
    0.45
     fá
    0.44
     Last
    0.44
     Empty
    0.43
     outer
    0.43
     =
    0.43
    न
    0.42
    Act Density 0.008%

    No Known Activations