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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tb
    -0.07
     ww
    -0.07
     blat
    -0.06
    bson
    -0.06
     Glide
    -0.06
    _keep
    -0.06
    比较
    -0.06
    Markers
    -0.06
    Los
    -0.06
     Hus
    -0.06
    POSITIVE LOGITS
     economy
    0.07
    �
    0.06
    ارف
    0.06
     Saskatchewan
    0.06
     Prov
    0.06
    .setY
    0.06
     TestCase
    0.06
    .transitions
    0.06
    _GENER
    0.06
     decre
    0.06
    Act Density 0.011%

    No Known Activations