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

    Neuronpedia

    INDEX
    Explanations

    shortage of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     an
    0.81
     in
    0.71
     as
    0.70
     o
    0.68
     Overwatch
    0.66
     a
    0.63
    ร้อง
    0.63
    ك
    0.63
     It
    0.62
     n
    0.62
    POSITIVE LOGITS
    t
    1.12
    at
    0.95
     shortages
    0.86
    n
    0.84
    el
    0.83
     overcrowding
    0.80
    -
    0.79
    ᱖
    0.79
    ut
    0.79
    liness
    0.79
    Act Density 0.006%

    No Known Activations