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

    Neuronpedia

    INDEX
    Explanations

    most

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    noop
    -0.06
     UserControl
    -0.06
     Hàn
    -0.06
     khác
    -0.06
    uggested
    -0.06
     stát
    -0.06
     IMP
    -0.06
     hại
    -0.06
    @stop
    -0.06
    руг
    -0.06
    POSITIVE LOGITS
     Winter
    0.07
     pulls
    0.07
    による
    0.06
     animals
    0.06
     Liberty
    0.06
    =train
    0.06
     peppers
    0.06
     partnership
    0.06
     events
    0.06
    كيل
    0.06
    Act Density 0.039%

    No Known Activations