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

    Neuronpedia

    INDEX
    Explanations

    Numerical measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     доб
    -0.07
    微软雅黑
    -0.06
     cops
    -0.06
     sagen
    -0.06
     fluorescence
    -0.06
     criminals
    -0.06
    .Team
    -0.06
     petitions
    -0.06
    θο
    -0.06
     geography
    -0.06
    POSITIVE LOGITS
     nive
    0.07
     annum
    0.07
     수도
    0.06
     реги
    0.06
    αρίου
    0.06
    ordial
    0.06
    acak
    0.06
     بده
    0.06
    udiantes
    0.06
    .slim
    0.06
    Act Density 0.050%

    No Known Activations