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

    Neuronpedia

    INDEX
    Explanations

    Reform

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ыты
    -0.09
    uelen
    -0.08
     Maint
    -0.08
     traveled
    -0.08
    vence
    -0.08
     například
    -0.07
    สอง
    -0.07
    -ke
    -0.07
     travelled
    -0.07
    utenant
    -0.07
    POSITIVE LOGITS
     overhaul
    0.11
    改革
    0.11
     reorgan
    0.10
     reforms
    0.10
     reforma
    0.10
     redesign
    0.10
     reform
    0.09
     privat
    0.09
     redesigned
    0.09
     restructure
    0.09
    Act Density 0.028%

    No Known Activations