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

    Neuronpedia

    INDEX
    Explanations

    burden or load

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     letz
    -0.09
     ing
    -0.09
     Tweets
    -0.08
     lul
    -0.08
     humili
    -0.08
     spending
    -0.08
    ĵ¨
    -0.08
     tem
    -0.08
     Ing
    -0.08
    Override
    -0.07
    POSITIVE LOGITS
     burden
    0.66
     load
    0.54
    è´Ł
    0.46
    load
    0.44
     Load
    0.44
     burdens
    0.43
    bur
    0.41
     нагÑĢÑĥз
    0.41
    è²ł
    0.39
    Load
    0.38
    Act Density 0.156%

    No Known Activations