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

    Neuronpedia

    INDEX
    Explanations

    size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     presidential
    -0.07
     Kok
    -0.06
     Falls
    -0.06
     Baker
    -0.06
     останні
    -0.06
     deterior
    -0.06
    -country
    -0.06
     forest
    -0.06
    .Client
    -0.06
     Toolkit
    -0.06
    POSITIVE LOGITS
    alertView
    0.07
    иплом
    0.07
     JVM
    0.07
     сер
    0.07
    setEnabled
    0.06
    .ps
    0.06
    setContent
    0.06
     Wu
    0.06
    ляет
    0.06
     mattresses
    0.06
    Act Density 0.054%

    No Known Activations