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

    Neuronpedia

    INDEX
    Explanations

    do

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     capability
    -0.07
    Develop
    -0.07
    Powered
    -0.07
     leans
    -0.06
    (@
    -0.06
    AMED
    -0.06
     crowded
    -0.06
    Localized
    -0.06
     fearful
    -0.06
     elimination
    -0.06
    POSITIVE LOGITS
     موضوع
    0.07
    押
    0.06
    _dat
    0.06
    ่าจะ
    0.06
     dens
    0.06
    .wik
    0.06
     pData
    0.06
     edilm
    0.06
    asn
    0.06
    における
    0.06
    Act Density 0.004%

    No Known Activations