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

    Neuronpedia

    INDEX
    Explanations

    sources of funds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Laboratory
    0.86
     国
    0.77
    Laboratory
    0.77
     Countries
    0.77
     Landscapes
    0.77
     Campground
    0.76
    Films
    0.75
    我对
    0.75
     മണ്ണി
    0.75
     Roads
    0.75
    POSITIVE LOGITS
     overpriced
    0.68
     inflate
    0.66
     tini
    0.65
    तन
    0.64
     inú
    0.63
     hefty
    0.62
     cuddle
    0.62
     deviated
    0.62
     задума
    0.62
     своей
    0.61
    Act Density 0.002%

    No Known Activations