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

    Neuronpedia

    INDEX
    Explanations

    econ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    caracter
    -0.07
    캇
    -0.07
    迥
    -0.07
    borne
    -0.07
     manera
    -0.07
     işlem
    -0.07
    Curso
    -0.07
    這種
    -0.07
    脸部
    -0.07
     категории
    -0.07
    POSITIVE LOGITS
    рит
    0.07
     tribunal
    0.07
     снижен
    0.07
     Manufact
    0.07
     residents
    0.07
    ystals
    0.07
     з
    0.07
     fri
    0.07
    herit
    0.06
     temples
    0.06
    Act Density 0.002%

    No Known Activations