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

    Neuronpedia

    INDEX
    Explanations

    still the acting president

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unwarranted
    0.57
     dovrà
    0.55
     devrez
    0.51
    ری
    0.48
     vaisseau
    0.47
     forêt
    0.45
     inapplicable
    0.44
     getWorld
    0.44
    ها
    0.44
     necessitated
    0.44
    POSITIVE LOGITS
    quality
    0.48
     oran
    0.45
     dets
    0.45
     profesion
    0.43
    prof
    0.43
    known
    0.43
    job
    0.42
     cooperation
    0.42
    http
    0.42
    hrad
    0.42
    Act Density 0.001%

    No Known Activations