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

    Neuronpedia

    INDEX
    Explanations

    research reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sale
    -0.07
     cds
    -0.07
     mínimo
    -0.07
     tenure
    -0.06
     日期
    -0.06
     drought
    -0.06
     activate
    -0.06
     PROGRAM
    -0.06
    configured
    -0.06
    Valor
    -0.06
    POSITIVE LOGITS
    navbar
    0.07
    paration
    0.07
     una
    0.07
     Axios
    0.06
    άσ
    0.06
    Got
    0.06
     ủy
    0.06
     pap
    0.06
     ineff
    0.06
    剩
    0.06
    Act Density 0.071%

    No Known Activations